Publications by Junichi Yamagishi
jyamagis.bib
@article{analysis-hts-adaptation-junichi,
author = {Junichi Yamagishi and Takao Kobayashi and Yuji Nakano
and Katsumi Ogata and Juri Isogai},
title = {Analysis of Speaker Adaptation Algorihms for
{HMM}-based Speech Synthesis and a Constrained {SMAPLR}
Adaptation Algorithm},
journal = {IEEE Transactions on Audio, Speech and Language
Processing},
note = {In print},
abstract = {In this paper we analyze the effects of several
factors and configuration choices encountered during
training and model construction when we want to obtain
better and more stable adaptation in HMM-based speech
synthesis. We then propose a new adaptation algorithm
called constrained structural maximum a posteriori
linear regression (CSMAPLR) whose derivation is based
on the knowledge obtained in this analysis and on the
results of comparing several conventional adaptation
algorithms. Here we investigate six major aspects of
the speaker adaptation: initial models transform
functions, estimation criteria, and sensitivity of
several linear regression adaptation algorithms
algorithms. Analyzing the effect of the initial model,
we compare speaker-dependent models, gender-independent
models, and the simultaneous use of the
gender-dependent models to single use of the
gender-dependent models. Analyzing the effect of the
transform functions, we compare the transform function
for only mean vectors with that for mean vectors and
covariance matrices. Analyzing the effect of the
estimation criteria, we compare the ML criterion with a
robust estimation criterion called structural MAP. We
evaluate the sensitivity of several thresholds for the
piecewise linear regression algorithms and take up
methods combining MAP adaptation with the linear
regression algorithms. We incorporate these adaptation
algorithms into our speech synthesis system and present
several subjective and objective evaluation results
showing the utility and effectiveness of these
algorithms in speaker adaptation for HMM-based speech
synthesis.},
categories = {speech synthesis, HMM-based speech synthesis, HTS,
speaker adaptation, voice conversion, average voice},
key = {analysis-hts-adaptation-junichi},
year = 2008
}
@inproceedings{anderssoncabral09,
author = {J. Sebastian Andersson and Joao P. Cabral and Leonardo
Badino and Junichi Yamagishi and Robert A.J. Clark},
title = {Glottal Source and Prosodic Prominence Modelling in
{HMM}-based Speech Synthesis for the {B}lizzard
{C}hallenge 2009},
booktitle = {The Blizzard Challenge 2009},
address = {Edinburgh, U.K.},
abstract = {This paper describes the CSTR entry for the Blizzard
Challenge 2009. The work focused on modifying two parts
of the Nitech 2005 HTS speech synthesis system to
improve naturalness and contextual appropriateness. The
first part incorporated an implementation of the
Linjencrants-Fant (LF) glottal source model. The second
part focused on improving synthesis of prosodic
prominence including emphasis through context dependent
phonemes. Emphasis was assigned to the synthesised test
sentences based on a handful of theory based rules. The
two parts (LF-model and prosodic prominence) were not
combined and hence evaluated separately. The results on
naturalness for the LF-model showed that it is not yet
perceived as natural as the Benchmark HTS system for
neutral speech. The results for the prosodic prominence
modelling showed that it was perceived as contextually
appropriate as the Benchmark HTS system, despite a low
naturalness score. The Blizzard challenge evaluation
has provided valuable information on the status of our
work and continued work will begin with analysing why
our modifications resulted in reduced naturalness
compared to the Benchmark HTS system.},
categories = {HMM, HTS, speech synthesis, LF-model, glottal source,
prosodic prominence, emphasis},
month = sep,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2009/cstr_Blizzard2009.pdf},
year = 2009
}
@article{treeboosting-junichi,
author = {Junichi Yamagishi and Hisashi Kawai and Takao
Kobayashi},
title = {Phone Duration Modeling Using Gradient Tree Boosting},
journal = {Speech Communication},
volume = 50,
number = 5,
pages = {405--415},
note = {},
abstract = { In text-to-speech synthesis systems, phone duration
influences the quality and naturalness of synthetic
speech. In this study, we incorporate an ensemble
learning technique called gradient tree boosting into
phone duration modeling as an alternative to the
conventional approach using regression trees, and
objectively evaluate the prediction accuracy of
Japanese, Mandarin, and English phone duration. The
gradient tree boosting algorithm is a meta algorithm of
regression trees: it iteratively builds the regression
tree from the residuals and outputs weighting sum of
the regression trees. Our evaluation results show that
compared to the regression trees or other techniques
related to the regression trees, the gradient tree
boosting algorithm can substantially and robustly
improve the predictive accuracy of the phone duration
regardless of languages, speakers, or domains.},
categories = {Text-to-speech synthesis, Phone duration modeling,
Gradient tree boosing},
doi = {10.1016/j.specom.2007.12.003},
key = {treeboosting-junichi},
month = may,
year = 2008
}
@inproceedings{ling:richmond:yamagishi:wang:2008a,
author = {Ling, Zhen-Hua and Richmond, Korin and Yamagishi,
Junichi and Wang, Ren-Hua },
title = {Articulatory Control of {HMM}-based Parametric Speech
Synthesis Driven by Phonetic Knowledge},
booktitle = {Proc. Interspeech},
pages = {573--576},
address = {Brisbane, Australia},
abstract = {This paper presents a method to control the
characteristics of synthetic speech flexibly by
integrating articulatory features into a Hidden Markov
Model (HMM)-based parametric speech synthesis system.
In contrast to model adaptation and interpolation
approaches for speaking style control, this method is
driven by phonetic knowledge, and target speech samples
are not required. The joint distribution of parallel
acoustic and articulatory features considering
cross-stream feature dependency is estimated. At
synthesis time, acoustic and articulatory features are
generated simultaneously based on the
maximum-likelihood criterion. The synthetic speech can
be controlled flexibly by modifying the generated
articulatory features according to arbitrary phonetic
rules in the parameter generation process. Our
experiments show that the proposed method is effective
in both changing the overall character of synthesized
speech and in controlling the quality of a specific
vowel.},
categories = {speech synthesis, HMM, articulatory features, phonetic
knowledge},
key = {ling:richmond:yamagishi:wang:2008a},
month = sep,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/IS080582.PDF},
year = 2008
}
@article{Andersson2012175,
author = {Sebastian Andersson and Junichi Yamagishi and Robert
A.J. Clark},
title = {Synthesis and evaluation of conversational
characteristics in {HMM}-based speech synthesis},
journal = {Speech Communication},
volume = {54},
number = {2},
pages = {175--188},
note = {},
abstract = {Spontaneous conversational speech has many
characteristics that are currently not modelled well by
HMM-based speech synthesis and in order to build
synthetic voices that can give an impression of someone
partaking in a conversation, we need to utilise data
that exhibits more of the speech phenomena associated
with conversations than the more generally used
carefully read aloud sentences. In this paper we show
that synthetic voices built with HMM-based speech
synthesis techniques from conversational speech data,
preserved segmental and prosodic characteristics of
frequent conversational speech phenomena. An analysis
of an evaluation investigating the perception of
quality and speaking style of HMM-based voices confirms
that speech with conversational characteristics are
instrumental for listeners to perceive successful
integration of conversational speech phenomena in
synthetic speech. The achieved synthetic speech quality
provides an encouraging start for the continued use of
conversational speech in HMM-based speech synthesis.},
doi = {10.1016/j.specom.2011.08.001},
issn = {0167-6393},
keywords = {Speech synthesis, HMM, Conversation, Spontaneous
speech, Filled pauses, Discourse marker},
url = {http://www.sciencedirect.com/science/article/pii/S0167639311001178},
year = 2012
}
@inproceedings{cereproc-hts,
author = {Matthew P. Aylett and Junichi Yamagishi},
title = {Combining Statistical Parameteric Speech Synthesis and
Unit-Selection for Automatic Voice Cloning},
booktitle = {Proc. LangTech 2008},
address = {Brisbane, Australia},
abstract = {The ability to use the recorded audio of a subject’¡Çs
voice to produce an open-domain synthesis system has
generated much interest both in academic research and
in commercial speech technology. The ability to produce
synthetic versions of a subjects voice has potential
commercial applications, such as virtual celebrity
actors, or potential clinical applications, such as
offering a synthetic replacement voice in the case of a
laryngectomy. Recent developments in HMM-based speech
synthesis have shown it is possible to produce
synthetic voices from quite small amounts of speech
data. However, mimicking the depth and variation of a
speaker’¡Çs prosody as well as synthesising natural
voice quality is still a challenging research problem.
In contrast, unit-selection systems have shown it is
possible to strongly retain the character of the voice
but only with sufficient original source material.
Often this runs into hours and may require significant
manual checking and labelling. In this paper we will
present two state of the art systems, an HMM based
system HTS-2007, developed by CSTR and Nagoya Institute
Technology, and a commercial unit-selection system
CereVoice, developed by Cereproc. Both systems have
been used to mimic the voice of George W. Bush (43rd
president of the United States) using freely available
audio from the web. In addition we will present a
hybrid system which combines both technologies. We
demonstrate examples of synthetic voices created from
10, 40 and 210 minutes of randomly selected speech. We
will then discuss the underlying problems associated
with voice cloning using found audio, and the
scalability of our solution.},
categories = {speech synthesis, HMM-based speech synthesis, HTS,
speaker adaptation, voice conversion, average voice},
key = {cereproc-hts},
month = sep,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/03_AYLETT.pdf},
year = 2008
}
@inproceedings{lingIS2012,
author = {Ling, Zhen-Hua and Richmond, Korin and Yamagishi,
Junichi},
title = {Vowel Creation by Articulatory Control in {HMM}-based
Parametric Speech Synthesis},
booktitle = {Proc. Interspeech},
address = {Portland, Oregon, USA},
abstract = { This paper presents a method to produce a new vowel
by articulatory control in hidden Markov model (HMM)
based parametric speech synthesis. A multiple
regression HMM (MRHMM) is adopted to model the
distribution of acoustic features, with articulatory
features used as external auxiliary variables. The
dependency between acoustic and articulatory features
is modelled by a group of linear transforms that are
either estimated context-dependently or determined by
the distribution of articulatory features. Vowel
identity is removed from the set of context features
used to ensure compatibility between the
context-dependent model parameters and the articulatory
features of a new vowel. At synthesis time, acoustic
features are predicted according to the input
articulatory features as well as context information.
With an appropriate articulatory feature sequence, a
new vowel can be generated even when it does not exist
in the training set. Experimental results show this
method is effective in creating the English vowel /2/
by articulatory control without using any acoustic
samples of this vowel.},
categories = {Speech synthesis, articulatory features,
multiple-regression hidden Markov model},
keywords = {Speech synthesis, articulatory features,
multiple-regression hidden Markov model},
month = sep,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2012/LingRichmondYamagishi_IS2012.pdf},
year = 2012
}
@inproceedings{jyamagis07:avss2006,
author = {Junichi Yamagishi and Takao Kobayashi and Steve Renals
and Simon King and Heiga Zen and Tomoki Toda and
Keiichi Tokuda },
title = {Improved Average-Voice-based Speech Synthesis Using
Gender-Mixed Modeling and a Parameter Generation
Algorithm Considering {GV}},
booktitle = {Proc. 6th ISCA Workshop on Speech Synthesis (SSW-6)},
abstract = {For constructing a speech synthesis system which can
achieve diverse voices, we have been developing a
speaker independent approach of HMM-based speech
synthesis in which statistical average voice models are
adapted to a target speaker using a small amount of
speech data. In this paper, we incorporate a
high-quality speech vocoding method STRAIGHT and a
parameter generation algorithm with global variance
into the system for improving quality of synthetic
speech. Furthermore, we introduce a feature-space
speaker adaptive training algorithm and a gender mixed
modeling technique for conducting further normalization
of the average voice model. We build an English
text-to-speech system using these techniques and show
the performance of the system.},
categories = {HMM, speech synthesis, speaker adaptation, HTS},
month = aug,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2007/ssw6-yamagishi.pdf},
year = 2007
}
@article{6289354,
author = {Ling, Z. and Richmond, K. and Yamagishi, J.},
title = {Articulatory Control of {HMM}-based Parametric Speech
Synthesis using Feature-Space-Switched Multiple
Regression},
journal = {Audio, Speech, and Language Processing, IEEE
Transactions on},
volume = {21},
number = {1},
pages = {207--219},
abstract = {In previous work we proposed a method to control the
characteristics of synthetic speech flexibly by
integrating articulatory features into a hidden Markov
model (HMM) based parametric speech synthesiser. In
this method, a unified acoustic-articulatory model is
trained, and context-dependent linear transforms are
used to model the dependency between the two feature
streams. In this paper, we go significantly further and
propose a feature-space-switched multiple regression
HMM to improve the performance of articulatory control.
A multiple regression HMM (MRHMM) is adopted to model
the distribution of acoustic features, with
articulatory features used as exogenous explanatory
variables. A separate Gaussian mixture model (GMM) is
introduced to model the articulatory space, and
articulatory-to-acoustic regression matrices are
trained for each component of this GMM, instead of for
the context-dependent states in the HMM. Furthermore,
we propose a task-specific context feature tailoring
method to ensure compatibility between state context
features and articulatory features that are manipulated
at synthesis time. The proposed method is evaluated on
two tasks, using a speech database with acoustic
waveforms and articulatory movements recorded in
parallel by electromagnetic articulography (EMA). In a
vowel identity modification task, the new method
achieves better performance when reconstructing target
vowels by varying articulatory inputs than our previous
approach. A second vowel creation task shows our new
method is highly effective at producing a new vowel
from appropriate articulatory representations which,
even though no acoustic samples for this vowel are
present in the training data, is shown to sound highly
natural.},
doi = {10.1109/TASL.2012.2215600},
issn = {1558-7916},
year = 2013
}
@inproceedings{zen:HTSoverview,
author = {Heiga Zen and Keiichiro Oura and Takashi Nose and
Junichi Yamagishi and Shinji Sako and Tomoki Toda and
Takashi Masuko and Alan W. Black and Keiichi Tokuda},
title = {Recent development of the {HMM}-based speech synthesis
system ({HTS})},
booktitle = {Proc. 2009 Asia-Pacific Signal and Information
Processing Association (APSIPA)},
address = {Sapporo, Japan},
abstract = {A statistical parametric approach to speech synthesis
based on hidden Markov models (HMMs) has grown in
popularity over the last few years. In this approach,
spectrum, excitation, and duration of speech are
simultaneously modeled by context-dependent HMMs, and
speech waveforms are generate from the HMMs themselves.
Since December 2002, we have publicly released an
open-source software toolkit named “HMM-based speech
synthesis system (HTS)†to provide a research and
development toolkit for statistical parametric speech
synthesis. This paper describes recent developments of
HTS in detail, as well as future release plans.},
month = oct,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2009/zen_APSIPA2009.pdf},
year = 2009
}
@inproceedings{hirai07:5ms2007,
author = {Toshio Hirai and Junichi Yamagishi and Seiichi Tenpaku
},
title = {Utilization of an {HMM}-Based Feature Generation
Module in 5 ms Segment Concatenative Speech Synthesis},
booktitle = {Proc. 6th ISCA Workshop on Speech Synthesis (SSW-6)},
abstract = {If a concatenative speech synthesis system uses more
short speech segments, it increases the potential to
generate natural speech because the concatenation
variation becomes greater. Recently, a synthesis
approach was proposed in which very short (5 ms)
segments are used. In this paper, an implementation of
an HMM-based feature generation module into a very
short segment concatenative synthesis system that has
the advantage of modularity and a synthesis experiment
are described.},
categories = {speech synthesis, HTS, hybrid algorithm},
month = aug,
year = 2007
}
@inproceedings{CassiaICASSP12,
author = {Valentini-Botinhao, C. and Maia, R. and Yamagishi, J.
and King, S. and Zen, H.},
title = {{Cepstral analysis based on the Glimpse proportion
measure for improving the intelligibility of
{HMM}-based synthetic speech in noise}},
booktitle = {Proc. ICASSP},
pages = {3997--4000},
address = {Kyoto, Japan},
abstract = {In this paper we introduce a new cepstral coefficient
extraction method based on an intelligibility measure
for speech in noise, the Glimpse Proportion measure.
This new method aims to increase the intelligibility of
speech in noise by modifying the clean speech, and has
applications in scenarios such as public announcement
and car navigation systems. We first explain how the
Glimpse Proportion measure operates and further show
how we approximated it to integrate it into an existing
spectral envelope parameter extraction method commonly
used in the HMM-based speech synthesis framework. We
then demonstrate how this new method changes the
modelled spectrum according to the characteristics of
the noise and show results for a listening test with
vocoded and HMM-based synthetic speech. The test
indicates that the proposed method can significantly
improve intelligibility of synthetic speech in speech
shaped noise.},
categories = {HMM-based speech synthesis, intelligibility
enhancement, speech analysis},
doi = {10.1109/ICASSP.2012.6288794},
month = {March},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2012/Cassia_ICASSP12.pdf},
year = 2012
}
@inproceedings{ling_interspeech2010,
author = {Ling, Zhen-Hua and Richmond, Korin and Yamagishi,
Junichi},
title = {{HMM}-based Text-to-Articulatory-Movement Prediction
and Analysis of Critical Articulators},
booktitle = {Proc. Interspeech},
pages = {2194--2197},
address = {Makuhari, Japan},
abstract = {In this paper we present a method to predict the
movement of a speaker's mouth from text input using
hidden Markov models (HMM). We have used a corpus of
human articulatory movements, recorded by
electromagnetic articulography (EMA), to train HMMs. To
predict articulatory movements from text, a suitable
model sequence is selected and the maximum-likelihood
parameter generation (MLPG) algorithm is used to
generate output articulatory trajectories. In our
experiments, we find that fully context-dependent
models outperform monophone and quinphone models,
achieving an average root mean square (RMS) error of
1.945mm when state durations are predicted from text,
and 0.872mm when natural state durations are used.
Finally, we go on to analyze the prediction error for
different EMA dimensions and phone types. We find a
clear pattern emerges that the movements of so-called
critical articulators can be predicted more accurately
than the average performance.},
keywords = {Hidden Markov model, articulatory features, parameter
generation, critical articulators},
month = {September},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2010/IS100349.pdf},
year = 2010
}
@inproceedings{PhillipIS2012,
author = {Phillip L. De Leon and Bryan Stewart and Junichi
Yamagishi},
title = {Synthetic Speech Discrimination using Pitch Pattern
Statistics Derived from Image Analysis},
booktitle = {Proc. Interspeech},
address = {Portland, Oregon, USA},
abstract = { In this paper, we extend the work by Ogihara, et al.
to discriminate between human and synthetic speech
using features based on pitch patterns. As previously
demonstrated, significant differences in pitch patterns
between human and synthetic speech can be leveraged to
classify speech as being human or synthetic in origin.
We propose using mean pitch stability, mean pitch
stability range, and jitter as features extracted after
image analysis of pitch patterns. We have observed that
for synthetic speech, these features lie in a small and
distinct space as compared to human speech and have
modeled them with a multivariate Gaussian distribution.
Our classifier is trained using synthetic speech
collected from the 2008 and 2011 Blizzard Challenge
along with Festival pre-built voices and human speech
from the NIST2002 corpus. We evaluate the classifier on
a much larger corpus than previously studied using
human speech from the Switchboard corpus, synthetic
speech from the Resource Management corpus, and
synthetic speech generated from Festival trained on the
Wall Street Journal corpus. Results show 98% accuracy
in correctly classifying human speech and 96% accuracy
in correctly classifying synthetic speech.},
month = sep,
year = 2012
}
@article{roberto:specom2010,
author = {R. Barra-Chicote and J. Yamagishi and S. King and J.
Manuel Monero and J. Macias-Guarasa},
title = {Analysis of Statistical Parametric and Unit-Selection
Speech Synthesis Systems Applied to Emotional Speech},
journal = {Speech Communication},
volume = {52},
number = {5},
pages = {394--404},
abstract = {We have applied two state-of-the-art speech synthesis
techniques (unit selection and HMM-based synthesis) to
the synthesis of emotional speech. A series of
carefully designed perceptual tests to evaluate speech
quality, emotion identification rates and emotional
strength were used for the six emotions which we
recorded -- happiness, sadness, anger, surprise, fear,
disgust. For the HMM-based method, we evaluated
spectral and source components separately and
identified which components contribute to which
emotion. Our analysis shows that, although the HMM
method produces significantly better neutral speech,
the two methods produce emotional speech of similar
quality, except for emotions having context-dependent
prosodic patterns. Whilst synthetic speech produced
using the unit selection method has better emotional
strength scores than the HMM-based method, the
HMM-based method has the ability to manipulate the
emotional strength. For emotions that are characterized
by both spectral and prosodic components, synthetic
speech using unit selection methods was more accurately
identified by listeners. For emotions mainly
characterized by prosodic components, HMM-based
synthetic speech was more accurately identified. This
finding differs from previous results regarding
listener judgements of speaker similarity for neutral
speech. We conclude that unit selection methods require
improvements to prosodic modeling and that HMM-based
methods require improvements to spectral modeling for
emotional speech. Certain emotions cannot be reproduced
well by either method.},
doi = {10.1016/j.specom.2009.12.007},
keywords = {Emotional speech synthesis; HMM-based synthesis; Unit
selection},
month = may,
year = 2010
}
@inproceedings{5947571,
author = {Andraszewicz, S. and Yamagishi, J. and King, S.},
title = {Vocal attractiveness of statistical speech
synthesisers},
booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2011
IEEE International Conference on},
pages = {5368--5371},
abstract = {Our previous analysis of speaker-adaptive HMM-based
speech synthesis methods suggested that there are two
possible reasons why average voices can obtain higher
subjective scores than any individual adapted voice: 1)
model adaptation degrades speech quality proportionally
to the distance 'moved' by the transforms, and 2)
psychoacoustic effects relating to the attractiveness
of the voice. This paper is a follow-on from that
analysis and aims to separate these effects out. Our
latest perceptual experiments focus on attractiveness,
using average voices and speaker-dependent voices
without model trans formation, and show that using
several speakers to create a voice improves smoothness
(measured by Harmonics-to-Noise Ratio), reduces
distance from the the average voice in the log F0-F1
space of the final voice and hence makes it more
attractive at the segmental level. However, this is
weakened or overridden at supra-segmental or sentence
levels.},
doi = {10.1109/ICASSP.2011.5947571},
issn = {1520-6149},
keywords = {speaker-adaptive HMM-based speech synthesis
methods;speaker-dependent voices;statistical speech
synthesisers;vocal attractiveness;hidden Markov
models;speaker recognition;speech synthesis;},
month = may,
year = 2011
}
@inproceedings{Jaime2IS2012,
author = {J. Lorenzo and B. Martinez and R. Barra-Chicote and V.
Lopez–Ludena and J. Ferreiros and J. Yamagishi and
J.M. Montero},
title = { Towards an Unsupervised Speaking Style Voice Building
Framework: Multi–Style Speaker Diarization},
booktitle = {Proc. Interspeech},
address = {Portland, Oregon, USA},
abstract = { Current text–to–speech systems are developed
using studio-recorded speech in a neutral style or
based on acted emotions. However, the proliferation of
media sharing sites would allow developing a new
generation of speech–based systems which could cope
with sponta- neous and styled speech. This paper
proposes an architecture to deal with realistic
recordings and carries out some experiments on
unsupervised speaker diarization. In order to maximize
the speaker purity of the clusters while keeping a high
speaker coverage, the paper evaluates the F–measure
of a diarization module, achieving high scores (>85%)
especially when the clusters are longer than 30
seconds, even for the more spontaneous and expressive
styles (such as talk shows or sports).},
month = sep,
year = 2012
}
@incollection{sarah:hts09,
author = {Sarah Creer and Phil Green and Stuart Cunningham and
Junichi Yamagishi},
title = {Building personalised synthesised voices for
individuals with dysarthria using the {HTS} toolkit},
booktitle = {Computer Synthesized Speech Technologies: Tools for
Aiding Impairment},
publisher = {IGI Global},
editor = {John W. Mullennix and Steven E. Stern},
edition = {1st},
note = {in press},
abstract = {When the speech of an individual becomes
unintelligible due to a neurological disorder, a
synthesized voice can replace that of the individual.
To fully replace all functions of human speech
communication: communication of information,
maintenance of social relationships and displaying
identity, the voice must be intelligible,
natural-sounding and retain the vocal identity of the
speaker. For speakers with dysarthria, achieving this
output with minimal data recordings and deteriorating
speech is difficult. An alternative to this is using
Hidden Markov models (HMMs) which require much less
speech data than needed for concatenative methods, to
adapt a robust statistical model of speech towards the
speaker characteristics captured in the data recorded
by the individual. This chapter implements this
technique using the HTS toolkit to build personalized
synthetic voices for two individuals with dysarthria.
An evaluation of the voices by the participants
themselves suggests that this technique shows promise
for building and reconstructing personalized voices for
individuals with dysarthria once deterioration has
begun.},
year = 2009
}
@article{tuomo:ieee2011,
author = {T. Raitio and A. Suni and J. Yamagishi and H. Pulakka
and J. Nurminen and M. Vainio and P. Alku},
title = {{HMM}-Based Speech Synthesis Utilizing Glottal Inverse
Filtering},
journal = {IEEE Transactions on Audio, Speech and Language
Processing},
volume = 19,
number = 1,
pages = {153--165},
abstract = {This paper describes an hidden Markov model
(HMM)-based speech synthesizer that utilizes glottal
inverse filtering for generating natural sounding
synthetic speech. In the proposed method, speech is
first decomposed into the glottal source signal and the
model of the vocal tract filter through glottal inverse
filtering, and thus parametrized into excitation and
spectral features. The source and filter features are
modeled individually in the framework of HMM and
generated in the synthesis stage according to the text
input. The glottal excitation is synthesized through
interpolating and concatenating natural glottal flow
pulses, and the excitation signal is further modified
according to the spectrum of the desired voice source
characteristics. Speech is synthesized by filtering the
reconstructed source signal with the vocal tract
filter. Experiments show that the proposed system is
capable of generating natural sounding speech, and the
quality is clearly better compared to two HMM-based
speech synthesis systems based on widely used vocoder
techniques.},
doi = {10.1109/TASL.2010.2045239},
keywords = {Glottal inverse filtering , hidden Markov model (HMM)
, speech synthesis},
month = jan,
year = 2011
}
@inproceedings{Ayletetal09,
author = {Matthew P. Aylett and Simon King and Junichi Yamagishi},
title = {Speech Synthesis Without a Phone Inventory},
booktitle = {Interspeech},
pages = {2087--2090},
abstract = { In speech synthesis the unit inventory is decided
using phonological and phonetic expertise. This process
is resource intensive and potentially sub-optimal. In
this paper we investigate how acoustic clustering,
together with lexicon constraints, can be used to build
a self-organised inventory. Six English speech
synthesis systems were built using two frameworks, unit
selection and parametric HTS for three inventory
conditions: 1) a traditional phone set, 2) a system
using orthographic units, and 3) a self-organised
inventory. A listening test showed a strong preference
for the classic system, and for the orthographic system
over the self-organised system. Results also varied by
letter to sound complexity and database coverage. This
suggests the self-organised approach failed to
generalise pronunciation as well as introducing noise
above and beyond that caused by orthographic sound
mismatch.},
categories = {speech synthesis, unit selection, parametric
synthesis, phone inventory, orthographic synthesis},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2009/ma_interspeech09.pdf},
place = {Brighton},
year = 2009
}
@inproceedings{phillip:icassp2010,
author = {P. L. De Leon and V. R. Apsingekar and M. Pucher and
J. Yamagishi},
title = {Revisiting the security of speaker verification
systems against imposture using synthetic speech},
booktitle = {{Proc. ICASSP 2010}},
address = {Dallas, Texas, USA},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2010/main_r2.pdf},
year = 2010
}
@inproceedings{lingvowel,
author = {Ling, Zhenhua and Richmond, Korin and Yamagishi,
Junichi},
title = {Vowel Creation by Articulatory Control in {HMM}-based
Parametric Speech Synthesis},
booktitle = {Proc. The Listening Talker Workshop},
pages = {72},
address = {Edinburgh, UK},
month = {May},
pdf = {http://www.cstr.ed.ac.uk/downloads/publications/2012/Ling_etal_LISTA.pdf},
year = 2012
}
@article{JunichiHTS06,
author = {Junichi Yamagishi and Takao Kobayashi},
title = {Average-Voice-based Speech Synthesis using HSMM-based
Speaker Adaptation and Adaptive Training.},
journal = {IEICE Trans. Information and Systems},
volume = {E90-D},
number = 2,
pages = {533-543},
abstract = {In speaker adaptation for speech synthesis, it is
desirable to convert both voice characteristics and
prosodic features such as F0 and phone duration. For
simultaneous adaptation of spectrum, F0 and phone
duration within the HMM framework, we need to transform
not only the state output distributions corresponding
to spectrum and F0 but also the duration distributions
corresponding to phone duration. However, it is not
straightforward to adapt the state duration because the
original HMM does not have explicit duration
distributions. Therefore, we utilize the framework of
the hidden semi-Markov model (HSMM), which is an HMM
having explicit state duration distributions, and we
apply an HSMM-based model adaptation algorithm to
simultaneously transform both the state output and
state duration distributions. Furthermore, we propose
an HSMM-based adaptive training algorithm to
simultaneously normalize the state output and state
duration distributions of the average voice model. We
incorporate these techniques into our HSMM-based speech
synthesis system, and show their effectiveness from the
results of subjective and objective evaluation tests.},
month = feb,
year = 2007
}
@inproceedings{watts_yamagishi_king_2011,
author = {Oliver Watts and Junichi Yamagishi and Simon King},
title = {Unsupervised continuous-valued word features for
phrase-break prediction without a part-of-speech tagger},
booktitle = {Proc. Interspeech},
pages = {2157--2160},
address = {Florence, Italy},
abstract = {Part of speech (POS) tags are foremost among the
features conventionally used to predict intonational
phrase-breaks for text to speech (TTS) conversion. The
construction of such systems therefore presupposes the
availability of a POS tagger for the relevant language,
or of a corpus manually tagged with POS. However, such
tools and resources are not available in the majority
of the world’s languages, and manually labelling text
with POS tags is an expensive and time-consuming
process. We therefore propose the use of
continuous-valued features that summarise the
distributional characteristics of word types as
surrogates for POS features. Importantly, such features
are obtained in an unsupervised manner from an untagged
text corpus. We present results on the phrase-break
prediction task, where use of the features closes the
gap in performance between a baseline system (using
only basic punctuation-related features) and a topline
system (incorporating a state-of-the-art POS tagger).},
month = aug,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2011/watts_yamagishi_king_2011.pdf},
year = 2011
}
@inproceedings{Cassia_IS11,
author = {Valentini-Botinhao, Cassia and Yamagishi, Junichi and
King, Simon},
title = {Can Objective Measures Predict the Intelligibility of
Modified {HMM}-based Synthetic Speech in Noise?},
booktitle = {Proc. Interspeech},
abstract = {{Synthetic speech can be modified to improve
intelligibility in noise. In order to perform
modifications automatically, it would be useful to have
an objective measure that could predict the
intelligibility of modified synthetic speech for human
listeners. We analysed the impact on intelligibility
– and on how well objective measures predict it –
when we separately modify speaking rate, fundamental
frequency, line spectral pairs and spectral peaks.
Shifting LSPs can increase intelligibility for human
listeners; other modifications had weaker effects.
Among the objective measures we evaluated, the Dau
model and the Glimpse proportion were the best
predictors of human performance.}},
categories = {HMM-based speech synthesis, objective measures of
intelligibility},
month = aug,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2011/Cassia_IS11.pdf},
year = 2011
}
@inproceedings{robust-hts,
author = {Junichi Yamagishi and Zhenhua Ling and Simon King},
title = {Robustness of HMM-based Speech Synthesis},
booktitle = {Proc. Interspeech 2008},
pages = {581--584},
address = {Brisbane, Australia},
abstract = {As speech synthesis techniques become more advanced,
we are able to consider building high-quality voices
from data collected outside the usual highly-controlled
recording studio environment. This presents new
challenges that are not present in conventional
text-to-speech synthesis: the available speech data are
not perfectly clean, the recording conditions are not
consistent, and/or the phonetic balance of the material
is not ideal. Although a clear picture of the
performance of various speech synthesis techniques
(e.g., concatenative, HMM-based or hybrid) under good
conditions is provided by the Blizzard Challenge, it is
not well understood how robust these algorithms are to
less favourable conditions. In this paper, we analyse
the performance of several speech synthesis methods
under such conditions. This is, as far as we know, a
new research topic: ``Robust speech synthesis.'' As a
consequence of our investigations, we propose a new
robust training method for the HMM-based speech
synthesis in for use with speech data collected in
unfavourable conditions.},
categories = {speech synthesis, HMM-based speech synthesis, HTS,
speaker adaptation, voice conversion, average voice,
unit selection},
key = {robust-hts},
month = sep,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/RobustnessHTS.pdf},
year = 2008
}
@inproceedings{5947440,
author = {De Leon, P.L. and Hernaez, I. and Saratxaga, I. and
Pucher, M. and Yamagishi, J.},
title = {Detection of synthetic speech for the problem of
imposture},
booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2011
IEEE International Conference on},
pages = {4844--4847},
abstract = {In this paper, we present new results from our
research into the vulnerability of a speaker
verification (SV) system to synthetic speech. We use a
HMM-based speech synthesizer, which creates synthetic
speech for a targeted speaker through adaptation of a
background model and both GMM-UBM and support vector
machine (SVM) SV systems. Using 283 speakers from the
Wall-Street Journal (WSJ) corpus, our SV systems have a
0.35% EER. When the systems are tested with synthetic
speech generated from speaker models derived from the
WSJ journal corpus, over 91% of the matched claims are
accepted. We propose the use of relative phase shift
(RPS) in order to detect synthetic speech and develop a
GMM-based synthetic speech classifier (SSC). Using the
SSC, we are able to correctly classify human speech in
95% of tests and synthetic speech in 88% of tests thus
significantly reducing the vulnerability.},
doi = {10.1109/ICASSP.2011.5947440},
issn = {1520-6149},
keywords = {EER;GMM-UBM;GMM-based synthetic speech
classifier;HMM-based speech synthesizer;RPS;SSC;SV
system;WSJ corpus;Wall-Street Journal corpus;relative
phase shift;speaker verification system;support vector
machine;hidden Markov models;speaker recognition;speech
synthesis;support vector machines;},
month = may,
year = 2011
}
@article{nose07:mrhsmm,
author = {Takashi Nose and Junichi Yamagishi and Takao Kobayashi},
title = {A Style Control Technique for {HMM}-based Expressive
Speech Synthesis},
journal = {IEICE Trans. Information and Systems},
volume = {E90-D},
number = 9,
pages = {1406--1413},
abstract = {This paper describes a technique for controlling the
degree of expressivity of a desired emotional
expression and/or speaking style of synthesized speech
in an HMM-based speech synthesis framework. With this
technique, multiple emotional expressions and speaking
styles of speech are modeled in a single model by using
a multiple-regression hidden semi-Markov model
(MRHSMM). A set of control parameters, called the style
vector, is defined, and each speech synthesis unit is
modeled by using the MRHSMM, in which mean parameters
of the state output and duration distributions are
expressed by multiple-regression of the style vector.
In the synthesis stage, the mean parameters of the
synthesis units are modified by transforming an
arbitrarily given style vector that corresponds to a
point in a low-dimensional space, called style space,
each of whose coordinates represents a certain specific
speaking style or emotion of speech. The results of
subjective evaluation tests show that style and its
intensity can be controlled by changing the style
vector},
categories = {HMM-based speech synthesis, speaking style, emotional
expression, style interpolation, hidden semi-Markov
model (HSMM)},
month = sep,
url = {http://search.ieice.org/bin/summary.php?id=e90-d_9_1406&category=D&lang=E&year=2007&abst=},
year = 2007
}
@article{Ximera06,
author = {Hisashi Kawai and Tomoki Toda and Junichi Yamagishi
and Toshio Hirai and Jinfu Ni and Nobuyuki Nishizawa
and Minoru Tsuzaki and Keiichi Tokuda},
title = {XIMERA: a concatenative speech synthesis system with
large scale corpora},
journal = {IEICE Trans. Information and Systems},
volume = {J89-D-II},
number = 12,
pages = {2688-2698},
month = dec,
year = 2006
}
@article{ling2008,
author = {Ling, Z. and Richmond, K. and Yamagishi, J. and Wang,
R.},
title = {Integrating Articulatory Features into {HMM}-based
Parametric Speech Synthesis},
journal = {IEEE Transactions on Audio, Speech and Language
Processing },
volume = 17,
number = 6,
pages = {1171--1185},
note = {\textbf{IEEE SPS 2010 Young Author Best Paper Award}},
abstract = {This paper presents an investigation of ways to
integrate articulatory features into Hidden Markov
Model (HMM)-based parametric speech synthesis,
primarily with the aim of improving the performance of
acoustic parameter generation. The joint distribution
of acoustic and articulatory features is estimated
during training and is then used for parameter
generation at synthesis time in conjunction with a
maximum-likelihood criterion. Different model
structures are explored to allow the articulatory
features to influence acoustic modeling: model
clustering, state synchrony and cross-stream feature
dependency. The results of objective evaluation show
that the accuracy of acoustic parameter prediction can
be improved when shared clustering and
asynchronous-state model structures are adopted for
combined acoustic and articulatory features. More
significantly, our experiments demonstrate that
modeling the dependency between these two feature
streams can make speech synthesis more flexible. The
characteristics of synthetic speech can be easily
controlled by modifying generated articulatory features
as part of the process of acoustic parameter
generation.},
categories = {Speech synthesis, articulation, HMM-based synthesis},
doi = {10.1109/TASL.2009.2014796},
key = {ling2008},
month = aug,
year = 2009
}
@inproceedings{child_synthesis_2009,
author = {Oliver Watts and Junichi Yamagishi and Simon King and
Kay Berkling},
title = {{HMM} Adaptation and Voice Conversion for the
Synthesis of Child Speech: A Comparison},
booktitle = {Proc. Interspeech 2009},
pages = {2627--2630},
address = {Brighton, U.K.},
abstract = {This study compares two different methodologies for
producing data-driven synthesis of child speech from
existing systems that have been trained on the speech
of adults. On one hand, an existing statistical
parametric synthesiser is transformed using model
adaptation techniques, informed by linguistic and
prosodic knowledge, to the speaker characteristics of a
child speaker. This is compared with the application of
voice conversion techniques to convert the output of an
existing waveform concatenation synthesiser with no
explicit linguistic or prosodic knowledge. In a
subjective evaluation of the similarity of synthetic
speech to natural speech from the target speaker, the
HMM-based systems evaluated are generally preferred,
although this is at least in part due to the higher
dimensional acoustic features supported by these
techniques.},
month = sep,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2009/child_synthesis_2009.pdf},
year = 2009
}
@article{anderssonyamagishi12,
author = {Andersson, S. and Yamagishi, J. and Clark, R.A.J.},
title = {Synthesis and Evaluation of Conversational
Characteristics in {HMM}-Based Speech Synthesis},
journal = {Speech Communication},
volume = 54,
number = 2,
pages = {175-188},
abstract = {Spontaneous conversational speech has many
characteristics that are currently not modelled well by
HMM-based speech synthesis and in order to build
synthetic voices that can give an impression of someone
partaking in a conversation, we need to utilise data
that exhibits more of the speech phenomena associated
with conversations than the more generally used
carefully read aloud sentences. In this paper we show
that synthetic voices built with HMM-based speech
synthesis techniques from conversational speech data,
preserved segmental and prosodic characteristics of
frequent conversational speech phenomena. An analysis
of an evaluation investigating the perception of
quality and speaking style of HMM-based voices confirms
that speech with conversational characteristics are
instrumental for listeners to perceive successful
integration of conversational speech phenomena in
synthetic speech. The achieved synthetic speech quality
provides an encouraging start for the continued use of
conversational speech in HMM-based speech synthesis.},
doi = {10.1016/j.specom.2011.08.001},
year = 2012
}
@inproceedings{yong:ssw7,
author = {Yong Guan and Jilei Tian and Yi-Jian Wu and Junichi
Yamagishi and Jani Nurminen},
title = {A Unified and Automatic Approach Of {M}andarin {HTS}
System},
booktitle = {{Proc. SSW7}},
address = {Kyoto, Japan},
keywords = {HTS, speech synthesis, mandarin},
month = {September},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2010/HTS_Yong_ssw7.pdf},
year = 2010
}
@article{Dines2011,
author = {John Dines and Hui Liang and Lakshmi Saheer and
Matthew Gibson and William Byrne and Keiichiro Oura and
Keiichi Tokuda and Junichi Yamagishi and Simon King and
Mirjam Wester and Teemu Hirsimäki and Reima
Karhila and Mikko Kurimo},
title = {Personalising speech-to-speech translation:
Unsupervised cross-lingual speaker adaptation for
{HMM}-based speech synthesis},
journal = {Computer Speech and Language},
volume = {27},
number = {2},
pages = {420--437},
abstract = {In this paper we present results of unsupervised
cross-lingual speaker adaptation applied to
text-to-speech synthesis. The application of our
research is the personalisation of speech-to-speech
translation in which we employ a HMM statistical
framework for both speech recognition and synthesis.
This framework provides a logical mechanism to adapt
synthesised speech output to the voice of the user by
way of speech recognition. In this work we present
results of several different unsupervised and
cross-lingual adaptation approaches as well as an
end-to-end speaker adaptive speech-to-speech
translation system. Our experiments show that we can
successfully apply speaker adaptation in both
unsupervised and cross-lingual scenarios and our
proposed algorithms seem to generalise well for several
language pairs. We also discuss important future
directions including the need for better evaluation
metrics.},
doi = {10.1016/j.csl.2011.08.003},
issn = {0885-2308},
keywords = {Speech-to-speech translation, Cross-lingual speaker
adaptation, HMM-based speech synthesis, Speaker
adaptation, Voice conversion},
url = {http://www.sciencedirect.com/science/article/pii/S0885230811000441},
month = feb,
year = 2013
}
@inproceedings{avss-icassp07,
author = {J. Yamagishi and T. Kobayashi and M. Tachibana and K.
Ogata and Y. Nakano},
title = {Model adaptation approach to speech synthesis with
diverse voices and styles},
booktitle = {Proc. ICASSP},
pages = {1233--1236},
abstract = {In human computer interaction and dialogue systems, it
is often desirable for text-to-speech synthesis to be
able to generate natural sounding speech with an
arbitrary speaker~Afs voice and with varying speaking
styles and/or emotional expressions. We have developed
an average-voice-based speech synthesis method using
statistical average voice models and model adaptation
techniques for this purpose. In this paper, we describe
an overview of the speech synthesis system and show the
current performance with several experimental results.},
year = 2007
}
@inproceedings{lei2011a,
author = {Lei, Ming and Yamagishi, Junichi and Richmond, Korin
and Ling, Zhen-Hua and King, Simon and Dai, Li-Rong},
title = {Formant-controlled {HMM}-based speech synthesis},
booktitle = {Proc. Interspeech},
pages = {2777--2780},
address = {Florence, Italy},
abstract = {This paper proposes a novel framework that enables us
to manipulate and control formants in HMM-based speech
synthesis. In this framework, the dependency between
formants and spectral features is modelled by piecewise
linear transforms; formant parameters are effectively
mapped by these to the means of Gaussian distributions
over the spectral synthesis parameters. The spectral
envelope features generated under the influence of
formants in this way may then be passed to high-quality
vocoders to generate the speech waveform. This provides
two major advantages over conventional frameworks.
First, we can achieve spectral modification by changing
formants only in those parts where we want control,
whereas the user must specify all formants manually in
conventional formant synthesisers (e.g. Klatt). Second,
this can produce high-quality speech. Our results show
the proposed method can control vowels in the
synthesized speech by manipulating F 1 and F 2 without
any degradation in synthesis quality.},
categories = {speech synthesis, hidden Markov model, formants,
controllability},
month = {August},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2011/IS110769.pdf},
year = 2011
}
@inproceedings{cabral:renals:richmond:yamagishi:2008a,
author = {Cabral, J. and Renals, S. and Richmond, K. and
Yamagishi, J.},
title = {Glottal Spectral Separation for Parametric Speech
Synthesis},
booktitle = {Proc. Interspeech},
pages = {1829--1832},
address = {Brisbane, Australia},
abstract = {This paper presents a method to control the
characteristics of synthetic speech flexibly by
integrating articulatory features into a Hidden Markov
Model (HMM)-based parametric speech synthesis system.
In contrast to model adaptation and interpolation
approaches for speaking style control, this method is
driven by phonetic knowledge, and target speech samples
are not required. The joint distribution of parallel
acoustic and articulatory features considering
cross-stream feature dependency is estimated. At
synthesis time, acoustic and articulatory features are
generated simultaneously based on the
maximum-likelihood criterion. The synthetic speech can
be controlled flexibly by modifying the generated
articulatory features according to arbitrary phonetic
rules in the parameter generation process. Our
experiments show that the proposed method is effective
in both changing the overall character of synthesized
speech and in controlling the quality of a specific
vowel. },
categories = {HMM speech synthesis, Glottal Spectral Separation,
LF-model},
key = {cabral:renals:richmond:yamagishi:2008a},
month = sep,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/IS081086.PDF},
year = 2008
}
@inproceedings{zen07:hts-2,
author = {Heiga Zen and Takashi Nose and Junichi Yamagishi and
Shinji Sako and Takashi Masuko and Alan Black and
Keiichi Tokuda},
title = {The {HMM}-based speech synthesis system ({HTS})
version 2.0},
booktitle = {Proc. 6th ISCA Workshop on Speech Synthesis (SSW-6)},
abstract = {A statistical parametric speech synthesis system based
on hidden Markov models (HMMs) has grown in popularity
over the last few years. This system simultaneously
models spectrum, excitation, and duration of speech
using context-dependent HMMs and generates speech
waveforms from the HMMs themselves. Since December
2002, we have publicly released an open-source software
toolkit named HMM-based speech synthesis system (HTS)
to provide a research and development platform for the
speech synthesis community. In December 2006, HTS
version 2.0 was released. This version includes a
number of new features which are useful for both speech
synthesis researchers and developers. This paper
describes HTS version 2.0 in detail, as well as future
release plans.},
categories = {HMM, speech synthesis, HTS},
month = aug,
year = 2007
}
@article{john:ieee2011,
author = {J. Dines and J. Yamagishi and S. King},
title = {Measuring the gap between {HMM}-based {ASR} and {TTS}},
journal = {IEEE Selected Topics in Signal Processing},
note = {(in press)},
abstract = {The EMIME European project is conducting research in
the development of technologies for mobile,
personalised speech-to-speech translation systems. The
hidden Markov model (HMM) is being used as the
underlying technology in both automatic speech
recognition (ASR) and text-to-speech synthesis (TTS)
components, thus, the investigation of unified
statistical modelling approaches has become an implicit
goal of our research. As one of the first steps towards
this goal, we have been investigating commonalities and
differences between HMM-based ASR and TTS. In this
paper we present results and analysis of a series of
experiments that have been conducted on English ASR and
TTS systems measuring their performance with respect to
phone set and lexicon; acoustic feature type and
dimensionality; HMM topology; and speaker adaptation.
Our results show that, although the fundamental
statistical model may be essentially the same, optimal
ASR and TTS performance often demands diametrically
opposed system designs. This represents a major
challenge to be addressed in the investigation of such
unified modelling approaches.},
doi = {10.1109/JSTSP.2010.2079315},
keywords = {Acoustics, Adaptation model, Context modeling, Hidden
Markov models, Speech, Speech recognition, Training,
speech recognition, speech synthesis, unified models},
year = 2011
}
@inproceedings{dallIS2012,
author = {Dall, Rasmus and Veaux, Christophe and Yamagishi,
Junichi and King, Simon},
title = {Analysis of Speaker CLustering Strategies for
{HMM}-Based Speech Synthesis},
booktitle = {Proc. Interspeech},
address = {Portland, Oregon, USA},
abstract = {This paper describes a method for speaker clustering,
with the application of building average voice models
for speaker-adaptive HMM-based speech synthesis that
are a good basis for adapting to specific target
speakers. Our main hypothesis is that using
perceptually similar speakers to build the average
voice model will be better than use unselected
speakers, even if the amount of data available from
perceptually similar speakers is smaller. We measure
the perceived similarities among a group of 30 female
speakers in a listening test and then apply multiple
linear regression to automatically predict these
listener judgements of speaker similarity and thus to
identify similar speakers automatically. We then
compare a variety of average voice models trained on
either speakers who were perceptually judged to be
similar to the target speaker, or speakers selected by
the multiple linear regression, or a large global set
of unselected speakers. We find that the average voice
model trained on perceptually similar speakers provides
better performance than the global model, even though
the latter is trained on more data, confirming our main
hypothesis. However, the average voice model using
speakers selected automatically by the multiple linear
regression does not reach the same level of
performance.},
month = sep,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2012/DallIS2012.pdf},
year = 2012
}
@inproceedings{JaimeIS2012,
author = {Jaime Lorenzo-Trueba and Roberto Barra-Chicote and
Tuomo Raitio and Nicolas Obin and Paavo Alku and
Junichi Yamagishi and Juan M Montero},
title = { Towards Glottal Source Controllability in Expressive
Speech Synthesis},
booktitle = {Proc. Interspeech},
address = {Portland, Oregon, USA},
abstract = { In order to obtain more human like sounding human-
machine interfaces we must first be able to give them
expressive capabilities in the way of emotional and
stylistic features so as to closely adequate them to
the intended task. If we want to replicate those
features it is not enough to merely replicate the
prosodic information of fundamental frequency and
speaking rhythm. The proposed additional layer is the
modification of the glottal model, for which we make
use of the GlottHMM parameters. This paper analyzes the
viability of such an approach by verifying that the
expressive nuances are captured by the aforementioned
features, obtaining 95% recognition rates on styled
speaking and 82% on emotional speech. Then we evaluate
the effect of speaker bias and recording environment on
the source modeling in order to quantify possible
problems when analyzing multi-speaker databases.
Finally we propose a speaking styles separation for
Spanish based on prosodic features and check its
perceptual significance.},
month = sep,
year = 2012
}
@inproceedings{hts-child-oliver,
author = {Oliver Watts and Junichi Yamagishi and Kay Berkling
and Simon King},
title = {{HMM}-based synthesis of child speech},
booktitle = {Proc. of The 1st Workshop on Child, Computer and
Interaction (ICMI'08 post-conference workshop)},
address = {Crete, Greece},
abstract = {The synthesis of child speech presents challenges both
in the collection of data and in the building of a
synthesiser from that data. Because only limited data
can be collected, and the domain of that data is
constrained, it is difficult to obtain the type of
phonetically-balanced corpus usually used in speech
synthesis. As a consequence, building a synthesiser
from this data is difficult. Concatenative synthesisers
are not robust to corpora with many missing units (as
is likely when the corpus content is not carefully
designed), so we chose to build a statistical
parametric synthesiser using the HMM-based system HTS.
This technique has previously been shown to perform
well for limited amounts of data, and for data
collected under imperfect conditions. We compared 6
different configurations of the synthesiser, using both
speaker-dependent and speaker-adaptive modelling
techniques, and using varying amounts of data. The
output from these systems was evaluated alongside
natural and vocoded speech, in a Blizzard-style
listening test.},
categories = {speech synthesis, HMM-based speech synthesis, HTS,
speaker adaptation, voice conversion, average voice,
child speech},
key = {hts-child-oliver},
month = oct,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/child-hts-oliver.pdf},
year = 2008
}
@article{Oura2012703,
author = {Keiichiro Oura and Junichi Yamagishi and Mirjam Wester
and Simon King and Keiichi Tokuda},
title = {Analysis of unsupervised cross-lingual speaker
adaptation for {HMM}-based speech synthesis using
{KLD}-based transform mapping},
journal = {Speech Communication},
volume = {54},
number = {6},
pages = {703--714},
abstract = {In the EMIME project, we developed a mobile device
that performs personalized speech-to-speech translation
such that a user's spoken input in one language is used
to produce spoken output in another language, while
continuing to sound like the user's voice. We
integrated two techniques into a single architecture:
unsupervised adaptation for HMM-based TTS using
word-based large-vocabulary continuous speech
recognition, and cross-lingual speaker adaptation
(CLSA) for HMM-based TTS. The CLSA is based on a
state-level transform mapping learned using minimum
Kullback-Leibler divergence between pairs of HMM states
in the input and output languages. Thus, an
unsupervised cross-lingual speaker adaptation system
was developed. End-to-end speech-to-speech translation
systems for four languages (English, Finnish, Mandarin,
and Japanese) were constructed within this framework.
In this paper, the English-to-Japanese adaptation is
evaluated. Listening tests demonstrate that adapted
voices sound more similar to a target speaker than
average voices and that differences between supervised
and unsupervised cross-lingual speaker adaptation are
small. Calculating the KLD state-mapping on only the
first 10 mel-cepstral coefficients leads to huge
savings in computational costs, without any detrimental
effect on the quality of the synthetic speech.},
doi = {10.1016/j.specom.2011.12.004},
issn = {0167-6393},
keywords = {HMM-based speech synthesis, Unsupervised speaker
adaptation, Cross-lingual speaker adaptation,
Speech-to-speech translation},
url = {http://www.sciencedirect.com/science/article/pii/S0167639311001774},
year = 2012
}
@inproceedings{cabral_ssw7,
author = {Cabral, Jo{\~a}o and Renals, Steve and Richmond, Korin
and Yamagishi, Junichi},
title = {Transforming Voice Source Parameters in a {HMM}-based
Speech Synthesiser with Glottal Post-Filtering},
booktitle = {Proc. 7th ISCA Speech Synthesis Workshop (SSW7)},
pages = {365--370},
address = {NICT/ATR, Kyoto, Japan},
abstract = {Control over voice quality, e.g. breathy and tense
voice, is important for speech synthesis applications.
For example, transformations can be used to modify
aspects of the voice re- lated to speaker's identity
and to improve expressiveness. How- ever, it is hard to
modify voice characteristics of the synthetic speech,
without degrading speech quality. State-of-the-art sta-
tistical speech synthesisers, in particular, do not
typically al- low control over parameters of the
glottal source, which are strongly correlated with
voice quality. Consequently, the con- trol of voice
characteristics in these systems is limited. In con-
trast, the HMM-based speech synthesiser proposed in
this paper uses an acoustic glottal source model. The
system passes the glottal signal through a whitening
filter to obtain the excitation of voiced sounds. This
technique, called glottal post-filtering, allows to
transform voice characteristics of the synthetic speech
by modifying the source model parameters. We evaluated
the proposed synthesiser in a perceptual ex- periment,
in terms of speech naturalness, intelligibility, and
similarity to the original speaker's voice. The results
show that it performed as well as a HMM-based
synthesiser, which generates the speech signal with a
commonly used high-quality speech vocoder.},
keywords = {HMM-based speech synthesis, voice quality, glottal
post-filter},
month = {September},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2010/cabral_ssw7.pdf},
year = 2010
}
@inproceedings{tachibana07:styleclassify07,
author = {Makoto Tachibana and Keigo Kawashima and Junichi
Yamagishi and Takao Kobayashi},
title = {Performance Evaluation of {HMM}-Based Style
Classification with a Small Amount of Training Data},
booktitle = {Proc. Interspeech 2007},
abstract = {This paper describes a classification technique for
emotional expressions and speaking styles of speech
using only a small amount of training data of a target
speaker. We model spectral and fundamental frequency
(F0) features simultaneously using multi-space
probability distribution HMM (MSD-HMM), and adapt a
speaker-independent neutral style model to a certain
target speaker’s style model with a small amount of
data using MSD-MLLR which is extended MLLR for MSD-HMM.
We perform classification experiments for professional
narrators’ speech and non-professional speakers'
speech and evaluate the performance of proposed
technique by comparing with other commonly used
classifiers. We show that the proposed technique gives
better result than the other classifiers when using a
few sentences of target speaker’s style data.},
categories = {emotion, speaking style, classification},
month = aug,
year = 2007
}
@article{Ling2010834,
author = {Zhen-Hua Ling and Korin Richmond and Junichi Yamagishi},
title = {An Analysis of {HMM}-based prediction of articulatory
movements},
journal = {Speech Communication},
volume = {52},
number = {10},
pages = {834--846},
abstract = { This paper presents an investigation into predicting
the movement of a speaker's mouth from text input using
hidden Markov models (HMM). A corpus of human
articulatory movements, recorded by electromagnetic
articulography (EMA), is used to train HMMs. To predict
articulatory movements for input text, a suitable model
sequence is selected and a maximum-likelihood parameter
generation (MLPG) algorithm is used to generate output
articulatory trajectories. Unified
acoustic-articulatory HMMs are introduced to integrate
acoustic features when an acoustic signal is also
provided with the input text. Several aspects of this
method are analyzed in this paper, including the
effectiveness of context-dependent modeling, the role
of supplementary acoustic input, and the
appropriateness of certain model structures for the
unified acoustic-articulatory models. When text is the
sole input, we find that fully context-dependent models
significantly outperform monophone and quinphone
models, achieving an average root mean square (RMS)
error of 1.945 mm and an average correlation
coefficient of 0.600. When both text and acoustic
features are given as input to the system, the
difference between the performance of quinphone models
and fully context-dependent models is no longer
significant. The best performance overall is achieved
using unified acoustic-articulatory quinphone HMMs with
separate clustering of acoustic and articulatory model
parameters, a synchronous-state sequence, and a
dependent-feature model structure, with an RMS error of
0.900 mm and a correlation coefficient of 0.855 on
average. Finally, we also apply the same quinphone HMMs
to the acoustic-articulatory, or inversion, mapping
problem, where only acoustic input is available. An
average root mean square (RMS) error of 1.076 mm and an
average correlation coefficient of 0.812 are achieved.
Taken together, our results demonstrate how text and
acoustic inputs both contribute to the prediction of
articulatory movements in the method used.},
doi = {10.1016/j.specom.2010.06.006},
issn = {0167-6393},
keywords = {Hidden Markov model; Articulatory features; Parameter
generation},
month = {October},
year = 2010
}
@inproceedings{Cassia_ICASSP11,
author = {Valentini-Botinhao, Cassia and Yamagishi, Junichi and
King, Simon},
title = {Evaluation of objective measures for intelligibility
prediction of {HMM}-based synthetic speech in noise},
booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2011
IEEE International Conference on},
pages = {5112--5115},
abstract = {{In this paper we evaluate four objective measures of
speech with regards to intelligibility prediction of
synthesized speech in diverse noisy situations. We
evaluated three intelligibility measures, the Dau
measure, the glimpse proportion and the Speech
Intelligibility Index (SII) and a quality measure, the
Perceptual Evaluation of Speech Quality (PESQ). For the
generation of synthesized speech we used a state of the
art HMM-based speech synthesis system. The noisy
conditions comprised four additive noises. The measures
were compared with subjective intelligibility scores
obtained in listening tests. The results show the Dau
and the glimpse measures to be the best predictors of
intelligibility, with correlations of around 0.83 to
subjective scores. All measures gave less accurate
predictions of intelligibility for synthetic speech
than have previously been found for natural speech; in
particular the SII measure. In additional experiments,
we processed the synthesized speech by an ideal binary
mask before adding noise. The Glimpse measure gave the
most accurate intelligibility predictions in this
situation.}},
categories = {HMM-based speech synthesis, objective measures of
intelligibility},
doi = {10.1109/ICASSP.2011.5947507},
issn = {1520-6149},
month = may,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2011/Cassia_ICASSP11.pdf},
year = 2011
}
@inproceedings{leo_09-1,
author = {Leonardo Badino and J. Sebastian Andersson and Junichi
Yamagishi and Robert A.J. Clark},
title = {Identification of Contrast and Its Emphatic
Realization in {HMM}-based Speech Synthesis},
booktitle = {Proc. Interspeech 2009},
address = {Brighton, U.K.},
abstract = {The work presented in this paper proposes to identify
contrast in the form of contrastive word pairs and
prosodically signal it with emphatic accents in a
Text-to-Speech (TTS) application using a
Hidden-Markov-Model (HMM) based speech synthesis
system. We first describe a novel method to
automatically detect contrastive word pairs using
textual features only and report its performance on a
corpus of spontaneous conversations in English.
Subsequently we describe the set of features selected
to train a HMM-based speech synthesis system and
attempting to properly control prosodic prominence
(including emphasis). Results from a large scale
perceptual test show that in the majority of cases
listeners judge emphatic contrastive word pairs as
acceptable as their non-emphatic counterpart, while
emphasis on non-contrastive pairs is almost never
acceptable.},
month = sep,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2009/IS090749.PDF},
year = 2009
}
@misc{Hofer_Shimodaira:sigg:2007,
author = {Gregor Hofer and Hiroshi Shimodaira and Junichi
Yamagishi},
title = {Speech-driven Head Motion Synthesis based on a
Trajectory Model},
howpublished = {Poster at Siggraph 2007},
address = {San Diego, USA},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2007/siggraph07.pdf},
year = 2007
}
@article{yamagishi2009,
author = {Yamagishi, Junichi and Nose, Takashi and Zen, Heiga
and Ling, Zhenhua and Toda, Tomoki and Tokuda, Keiichi
and King, Simon and Renals, Steve},
title = {Robust Speaker-Adaptive {HMM}-based Text-to-Speech
Synthesis},
journal = {IEEE Transactions on Audio, Speech and Language
Processing},
volume = {17},
number = {6},
pages = {1208--1230},
abstract = {This paper describes a speaker-adaptive HMM-based
speech synthesis system. The new system, called
``HTS-2007,'' employs speaker adaptation (CSMAPLR+MAP),
feature-space adaptive training, mixed-gender modeling,
and full-covariance modeling using CSMAPLR transforms,
in addition to several other techniques that have
proved effective in our previous systems. Subjective
evaluation results show that the new system generates
significantly better quality synthetic speech than
speaker-dependent approaches with realistic amounts of
speech data, and that it bears comparison with
speaker-dependent approaches even when large amounts of
speech data are available. In addition, a comparison
study with several speech synthesis techniques shows
the new system is very robust: It is able to build
voices from less-than-ideal speech data and synthesize
good-quality speech even for out-of-domain sentences.},
pdf = {},
url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?isnumber=5109758&arnumber=5153555&count=14&index=12},
year = 2009
}
@inproceedings{phillip:odyssey2010,
author = {P.L. De Leon and M. Pucher and J. Yamagishi},
title = {Evaluation of the Vulnerability of Speaker
Verification to Synthetic Speech},
booktitle = {{Proc. Odyssey (The speaker and language recognition
workshop) 2010}},
address = {Brno, Czech Republic},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2010/main_v2.pdf},
year = 2010
}
@article{Stan2011442,
author = {Adriana Stan and Junichi Yamagishi and Simon King and
Matthew Aylett},
title = {The {R}omanian speech synthesis ({RSS}) corpus:
Building a high quality {HMM}-based speech synthesis
system using a high sampling rate},
journal = {Speech Communication},
volume = {53},
number = {3},
pages = {442--450},
note = {},
abstract = {This paper first introduces a newly-recorded high
quality Romanian speech corpus designed for speech
synthesis, called ``RSS'', along with Romanian
front-end text processing modules and HMM-based
synthetic voices built from the corpus. All of these
are now freely available for academic use in order to
promote Romanian speech technology research. The RSS
corpus comprises 3500 training sentences and 500 test
sentences uttered by a female speaker and was recorded
using multiple microphones at 96 kHz sampling
frequency in a hemianechoic chamber. The details of the
new Romanian text processor we have developed are also
given. Using the database, we then revisit some basic
configuration choices of speech synthesis, such as
waveform sampling frequency and auditory frequency
warping scale, with the aim of improving speaker
similarity, which is an acknowledged weakness of
current HMM-based speech synthesisers. As we
demonstrate using perceptual tests, these configuration
choices can make substantial differences to the quality
of the synthetic speech. Contrary to common practice in
automatic speech recognition, higher waveform sampling
frequencies can offer enhanced feature extraction and
improved speaker similarity for HMM-based speech
synthesis.},
doi = {10.1016/j.specom.2010.12.002},
issn = {0167-6393},
keywords = {Speech synthesis, HTS, Romanian, HMMs, Sampling
frequency, Auditory scale},
url = {http://www.sciencedirect.com/science/article/pii/S0167639310002074},
year = 2011
}
@inproceedings{oura:icassp:10,
author = {Keiichiro Oura and Keiichi Tokuda and Junichi
Yamagishi and Mirjam Wester and Simon King},
title = {Unsupervised Cross-lingual Speaker Adaptation for
{HMM}-based Speech Synthesis},
booktitle = {Proc. of ICASSP},
volume = {I},
pages = {4954-4957},
abstract = {In the EMIME project, we are developing a mobile
device that performs personalized speech-to-speech
translation such that a user's spoken input in one
language is used to produce spoken output in another
language, while continuing to sound like the user's
voice. We integrate two techniques, unsupervised
adaptation for HMM-based TTS using a word-based
large-vocabulary continuous speech recognizer and
cross-lingual speaker adaptation for HMM-based TTS,
into a single architecture. Thus, an unsupervised
cross-lingual speaker adaptation system can be
developed. Listening tests show very promising results,
demonstrating that adapted voices sound similar to the
target speaker and that differences between supervised
and unsupervised cross-lingual speaker adaptation are
small.},
categories = {speaker adaptation, TTS},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2010/oura_icassp2010.pdf},
year = 2010
}
@inproceedings{cabral_yrwst,
author = {J. Cabral and S. Renals and K. Richmond and J.
Yamagishi},
title = {{HMM}-based Speech Synthesis with an Acoustic Glottal
Source Model},
booktitle = {Proc. The First Young Researchers Workshop in Speech
Technology},
abstract = {A major cause of degradation of speech quality in
HMM-based speech synthesis is the use of a simple delta
pulse signal to generate the excitation of voiced
speech. This paper describes a new approach to using an
acoustic glottal source model in HMM-based
synthesisers. The goal is to improve speech quality and
parametric flexibility to better model and transform
voice characteristics.},
categories = {HMM-based Speech Synthesis, LF-Model, Glottal Spectral
Separation},
month = apr,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2009/jscabral-yrwss2009.pdf},
year = 2009
}
@article{Hashimoto2012857,
author = {Kei Hashimoto and Junichi Yamagishi and William Byrne
and Simon King and Keiichi Tokuda},
title = {Impacts of machine translation and speech synthesis on
speech-to-speech translation},
journal = {Speech Communication},
volume = {54},
number = {7},
pages = {857--866},
note = {},
abstract = {This paper analyzes the impacts of machine translation
and speech synthesis on speech-to-speech translation
systems. A typical speech-to-speech translation system
consists of three components: speech recognition,
machine translation and speech synthesis. Many
techniques have been proposed for integration of speech
recognition and machine translation. However,
corresponding techniques have not yet been considered
for speech synthesis. The focus of the current work is
machine translation and speech synthesis, and we
present a subjective evaluation designed to analyze
their impact on speech-to-speech translation. The
results of these analyses show that the naturalness and
intelligibility of the synthesized speech are strongly
affected by the fluency of the translated sentences. In
addition, several features were found to correlate well
with the average fluency of the translated sentences
and the average naturalness of the synthesized speech.},
doi = {10.1016/j.specom.2012.02.004},
issn = {0167-6393},
keywords = {Speech-to-speech translation, Machine translation,
Speech synthesis, Subjective evaluation},
url = {http://www.sciencedirect.com/science/article/pii/S0167639312000283},
year = 2012
}
@article{6205335,
author = {De Leon, P. L. and Pucher, M. and Yamagishi, J. and
Hernaez, I. and Saratxaga, I.},
title = {Evaluation of Speaker Verification Security and
Detection of {HMM}-Based Synthetic Speech},
journal = {Audio, Speech, and Language Processing, IEEE
Transactions on},
volume = {20},
number = {8},
pages = {2280--2290},
abstract = {In this paper, we evaluate the vulnerability of
speaker verification (SV) systems to synthetic speech.
The SV systems are based on either the Gaussian mixture
model #x2013;universal background model (GMM-UBM) or
support vector machine (SVM) using GMM supervectors. We
use a hidden Markov model (HMM)-based text-to-speech
(TTS) synthesizer, which can synthesize speech for a
target speaker using small amounts of training data
through model adaptation of an average voice or
background model. Although the SV systems have a very
low equal error rate (EER), when tested with synthetic
speech generated from speaker models derived from the
Wall Street Journal (WSJ) speech corpus, over 81% of
the matched claims are accepted. This result suggests
vulnerability in SV systems and thus a need to
accurately detect synthetic speech. We propose a new
feature based on relative phase shift (RPS),
demonstrate reliable detection of synthetic speech, and
show how this classifier can be used to improve
security of SV systems.},
doi = {10.1109/TASL.2012.2201472},
issn = {1558-7916},
month = oct,
year = 2012
}
@inproceedings{CassiaSAPA12,
author = {Valentini-Botinhao, C. and Yamagishi, J. and King, S.},
title = {{Speech intelligibility enhancement for {HMM}-based
synthetic speech in noise}},
booktitle = {Proc. Sapa Workshop},
address = {Portland, USA},
abstract = {It is possible to increase the intelligibility of
speech in noise by enhancing the clean speech signal.
In this paper we demonstrate the effects of modifying
the spectral envelope of synthetic speech according to
the environmental noise. To achieve this, we modify Mel
cepstral coefficients according to an intelligibility
measure that accounts for glimpses of speech in noise:
the Glimpse Proportion measure. We evaluate this method
against a baseline synthetic voice trained only with
normal speech and a topline voice trained with Lombard
speech, as well as natural speech. The intelligibility
of these voices was measured when mixed with
speech-shaped noise and with a competing speaker at
three different levels. The Lombard voices, both
natural and synthetic, were more intelligible than the
normal voices in all conditions. For speech-shaped
noise, the proposed modified voice was as intelligible
as the Lombard synthetic voice without requiring any
recordings of Lombard speech, which are hard to obtain.
However, in the case of competing talker noise, the
Lombard synthetic voice was more intelligible than the
proposed modified voice.},
categories = {HMM-based speech synthesis, intelligibility
enhancement},
month = {September},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2012/Cassia_Sapa12.pdf},
year = 2012
}
@inproceedings{jyamagis:emime,
author = {Junichi Yamagishi and Mike Lincoln and Simon King and
John Dines and Matthew Gibson and Jilei Tian and Yong
Guan},
title = {Analysis of Unsupervised and Noise-Robust
Speaker-Adaptive {HMM}-Based Speech Synthesis Systems
toward a Unified {ASR} and {TTS} Framework},
booktitle = {Proc. Interspeech 2009},
address = {Edinburgh, U.K.},
abstract = {For the 2009 Blizzard Challenge we have built an
unsupervised version of the HTS-2008 speaker-adaptive
HMM-based speech synthesis system for English, and a
noise robust version of the systems for Mandarin. They
are designed from a multidisciplinary application point
of view in that we attempt to integrate the components
of the TTS system with other technologies such as ASR.
All the average voice models are trained exclusively
from recognized, publicly available, ASR databases.
Multi-pass LVCSR and confidence scores calculated from
confusion network are used for the unsupervised
systems, and noisy data recorded in cars or public
spaces is used for the noise robust system. We believe
the developed systems form solid benchmarks and provide
good connections to ASR fields. This paper describes
the development of the systems and reports the results
and analysis of their evaluation.},
month = sep,
year = 2009
}
@inproceedings{CassiaLista12,
author = {Valentini-Botinhao, C. and Yamagishi, J. and King, S.},
title = {{Using an intelligibility measure to create noise
robust cepstral coefï¬cients for {HMM}-based speech
synthesis}},
booktitle = {Proc. LISTA Workshop},
address = {Edinburgh, UK},
categories = {HMM-based speech synthesis, intelligibility
enhancement},
month = {May},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2012/Cassia_Lista12.pdf},
year = 2012
}
@inproceedings{cabral2011a,
author = {Cabral, J.P. and Renals, S. and Yamagishi, J. and
Richmond, K.},
title = {{HMM}-based speech synthesiser using the {LF}-model of
the glottal source},
booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2011
IEEE International Conference on},
pages = {4704--4707},
abstract = {A major factor which causes a deterioration in speech
quality in {HMM}-based speech synthesis is the use of a
simple delta pulse signal to generate the excitation of
voiced speech. This paper sets out a new approach to
using an acoustic glottal source model in HMM-based
synthesisers instead of the traditional pulse signal.
The goal is to improve speech quality and to better
model and transform voice characteristics. We have
found the new method decreases buzziness and also
improves prosodic modelling. A perceptual evaluation
has supported this finding by showing a 55.6%
preference for the new system, as against the baseline.
This improvement, while not being as significant as we
had initially expected, does encourage us to work on
developing the proposed speech synthesiser further.},
categories = {HMM-based speech synthesiser;acoustic glottal source
model LF-model;delta pulse signal;perceptual
evaluation;prosodic modelling;speech quality;voiced
speech generation;hidden Markov models;speech
synthesis;},
doi = {10.1109/ICASSP.2011.5947405},
issn = {1520-6149},
month = may,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2011/05947405.pdf},
year = 2011
}
@misc{Hofer_Shimodaira:sca:2007,
author = {Gregor Hofer and Hiroshi Shimodaira and Junichi
Yamagishi},
title = {Lip motion synthesis using a context dependent
trajectory hidden {M}arkov model},
howpublished = {Poster at SCA 2007},
address = {San Diego, USA},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2007/sca07.pdf},
year = 2007
}
@inproceedings{higher_level,
author = {Oliver Watts and Junichi Yamagishi and Simon King},
title = {The role of higher-level linguistic features in
{HMM}-based speech synthesis},
booktitle = {Proc. Interspeech},
pages = {841-844},
address = {Makuhari, Japan},
abstract = {We analyse the contribution of higher-level elements
of the linguistic specification of a data-driven speech
synthesiser to the naturalness of the synthetic speech
which it generates. The system is trained using various
subsets of the full feature-set, in which features
relating to syntactic category, intonational phrase
boundary, pitch accent and boundary tones are
selectively removed. Utterances synthesised by the
different configurations of the system are then
compared in a subjective evaluation of their
naturalness. The work presented forms background
analysis for an ongoing set of experiments in
performing text-to-speech (TTS) conversion based on
shallow features: features that can be trivially
extracted from text. By building a range of systems,
each assuming the availability of a different level of
linguistic annotation, we obtain benchmarks for our
on-going work.},
month = sep,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2010/IS100565.pdf},
year = 2010
}
@inproceedings{tts_barra08,
author = {R. Barra-Chicote and J. Yamagishi and J.M. Montero and
S. King and S. Lutfi and J. Macias-Guarasa},
title = {Generacion de una voz sintetica en {C}astellano basada
en {HSMM} para la {E}valuacion {A}lbayzin 2008:
conversion texto a voz},
booktitle = {V Jornadas en Tecnologia del Habla},
pages = {115-118},
note = {(in Spanish)},
month = nov,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/tts-jth08.pdf},
year = 2008
}
@inproceedings{lips08-gregpr,
author = {Gregor Hofer and Junichi Yamagishi and Hiroshi
Shimodaira},
title = {Speech-driven Lip Motion Generation with a Trajectory
{HMM}},
booktitle = {Proc. Interspeech 2008},
pages = {2314--2317},
address = {Brisbane, Australia},
abstract = {Automatic speech animation remains a challenging
problem that can be described as finding the optimal
sequence of animation parameter configurations given
some speech. In this paper we present a novel technique
to automatically synthesise lip motion trajectories
from a speech signal. The developed system predicts lip
motion units from the speech signal and generates
animation trajectories automatically employing a
’¡ÉTrajectory Hidden Markov Model’¡É. Using the MLE
criterion, its parameter generation algorithm produces
the optimal smooth motion trajectories that are used to
drive control points on the lips directly.
Additionally, experiments were carried out to find a
suitable model unit that produces the most accurate
results. Finally a perceptual evaluation was conducted,
that showed that the developed motion units perform
better than phonemes.},
categories = {visual speech synthesis, trajectory HMM, HTS},
key = {lips08-gregpr},
month = sep,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/GregorLipsChallenge08.pdf},
year = 2008
}
@inproceedings{john:HTSGAP,
author = {J. Dines and J. Yamagishi and S. King},
title = {Measuring the gap between {HMM}-based {ASR} and {TTS}},
booktitle = {Proc. Interspeech},
pages = {1391--1394},
address = {Brighton, U.K.},
abstract = {The EMIME European project is conducting research in
the development of technologies for mobile,
personalised speech-to-speech translation systems. The
hidden Markov model is being used as the underlying
technology in both automatic speech recognition (ASR)
and text-to-speech synthesis (TTS) components, thus,
the investigation of unified statistical modelling
approaches has become an implicit goal of our research.
As one of the first steps towards this goal, we have
been investigating commonalities and differences
between HMM-based ASR and TTS. In this paper we present
results and analysis of a series of experiments that
have been conducted on English ASR and TTS systems,
measuring their performance with respect to phone set
and lexicon, acoustic feature type and dimensionality
and HMM topology. Our results show that, although the
fundamental statistical model may be essentially the
same, optimal ASR and TTS performance often demands
diametrically opposed system designs. This represents a
major challenge to be addressed in the investigation of
such unified modelling approaches.},
month = sep,
year = 2009
}
@inproceedings{kurimo:acl:10,
author = {Mikko Kurimo and William Byrne and John Dines and
Philip N. Garner and Matthew Gibson and Yong Guan and
Teemu Hirsim\"{a}ki and Reima Karhila and Simon King
and Hui Liang and Keiichiro Oura and Lakshmi Saheer and
Matt Shannon and Sayaka Shiota and Jilei Tian and
Keiichi Tokuda and Mirjam Wester and Yi-Jian Wu and
Junichi Yamagishi},
title = {Personalising speech-to-speech translation in the
{EMIME} project},
booktitle = {Proc. of the ACL 2010 System Demonstrations},
address = {Uppsala, Sweden},
abstract = {In the EMIME project we have studied unsupervised
cross-lingual speaker adaptation. We have employed an
HMM statistical framework for both speech recognition
and synthesis which provides transformation mechanisms
to adapt the synthesized voice in TTS (text-to-speech)
using the recognized voice in ASR (automatic speech
recognition). An important application for this
research is personalised speech-to-speech translation
that will use the voice of the speaker in the input
language to utter the translated sentences in the
output language. In mobile environments this enhances
the users' interaction across language barriers by
making the output speech sound more like the original
speaker's way of speaking, even if she or he could not
speak the output language.},
categories = {speaker adaptation},
month = {July},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2010/kurimo_acl_2010.pdf},
year = 2010
}
@inproceedings{cabral07,
author = {J. Cabral and S. Renals and K. Richmond and J.
Yamagishi},
title = {Towards an Improved Modeling of the Glottal Source in
Statistical Parametric Speech Synthesis},
booktitle = {Proc.of the 6th ISCA Workshop on Speech Synthesis},
address = {Bonn, Germany},
abstract = {This paper proposes the use of the Liljencrants-Fant
model (LF-model) to represent the glottal source signal
in HMM-based speech synthesis systems. These systems
generally use a pulse train to model the periodicity of
the excitation signal of voiced speech. However, this
model produces a strong and uniform harmonic structure
throughout the spectrum of the excitation which makes
the synthetic speech sound buzzy. The use of a mixed
band excitation and phase manipulation reduces this
effect but it can result in degradation of the speech
quality if the noise component is not weighted
carefully. In turn, the LF-waveform has a decaying
spectrum at higher frequencies, which is more similar
to the real glottal source excitation signal. We
conducted a perceptual experiment to test the
hypothesis that the LF-model can perform as well as or
better than the pulse train in a HMM-based speech
synthesizer. In the synthesis, we used the mean values
of the LF-parameters, calculated by measurements of the
recorded speech. The result of this study is important
not only regarding the improvement in speech quality of
these type of systems, but also because the LF-model
can be used to model many characteristics of the
glottal source, such as voice quality, which are
important for voice transformation and generation of
expressive speech.},
categories = {LF-model, Statistical parametric speech synthesis,
HMM-based speech synthesis},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2007/cabral07.pdf},
year = 2007
}
@article{michael09:dialectHTS,
author = {Michael Pucher and Dietmar Schabus and Junichi
Yamagishi and Friedrich Neubarth and Volker Strom},
title = {Modeling and Interpolation of {Austrian German and
Viennese} Dialect in {HMM}-based Speech Synthesis},
journal = {Speech Communication},
volume = {52},
number = {2},
pages = {164--179},
abstract = {An HMM-based speech synthesis framework is applied to
both Standard Austrian German and a Viennese dialectal
variety and several training strategies for
multi-dialect modeling such as dialect clustering and
dialect-adaptive training are investigated. For
bridging the gap between processing on the level of
HMMs and on the linguistic level, we add phonological
transformations to the HMM interpolation and apply them
to dialect interpolation. The crucial steps are to
employ several formalized phonological rules between
Austrian German and Viennese dialect as constraints for
the HMM interpolation. We verify the effectiveness of
this strategy in a number of perceptual evaluations.
Since the HMM space used is not articulatory but
acoustic space, there are some variations in evaluation
results between the phonological rules. However, in
general we obtained good evaluation results which show
that listeners can perceive both continuous and
categorical changes of dialect varieties by using
phonological transformations employed as switching
rules in the HMM interpolation.},
categories = {speech synthesis, hidden Markov model, dialect,
sociolect, Austrian German},
doi = {10.1016/j.specom.2009.09.004},
year = 2010
}
@inproceedings{king:tokuda:zen:yamagishi:interspeech2008,
author = {Simon King and Keiichi Tokuda and Heiga Zen and
Junichi Yamagishi},
title = {Unsupervised adaptation for HMM-based speech synthesis},
booktitle = {Proc. Interspeech},
pages = {1869-1872},
address = {Brisbane, Australia},
abstract = {It is now possible to synthesise speech using HMMs
with a comparable quality to unit-selection techniques.
Generating speech from a model has many potential
advantages over concatenating waveforms. The most
exciting is model adaptation. It has been shown that
supervised speaker adaptation can yield high-quality
synthetic voices with an order of magnitude less data
than required to train a speaker-dependent model or to
build a basic unit-selection system. Such supervised
methods require labelled adaptation data for the target
speaker. In this paper, we introduce a method capable
of unsupervised adaptation, using only speech from the
target speaker without any labelling.},
categories = {speech synthesis, HMM-based speech synthesis, HTS,
trajectory HMMs, speaker adaptation, MLLR},
month = {September},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/IS080299.PDF},
year = 2008
}
@article{child_speech_journal_2010,
author = {Watts, O. and Yamagishi, J. and King, S. and Berkling,
K.},
title = {Synthesis of Child Speech with {HMM} Adaptation and
Voice Conversion},
journal = {Audio, Speech, and Language Processing, IEEE
Transactions on},
volume = {18},
number = {5},
pages = {1005--1016},
abstract = {The synthesis of child speech presents challenges both
in the collection of data and in the building of a
synthesizer from that data. We chose to build a
statistical parametric synthesizer using the hidden
Markov model (HMM)-based system HTS, as this technique
has previously been shown to perform well for limited
amounts of data, and for data collected under imperfect
conditions. Six different configurations of the
synthesizer were compared, using both speaker-dependent
and speaker-adaptive modeling techniques, and using
varying amounts of data. For comparison with HMM
adaptation, techniques from voice conversion were used
to transform existing synthesizers to the
characteristics of the target speaker. Speaker-adaptive
voices generally outperformed child speaker-dependent
voices in the evaluation. HMM adaptation outperformed
voice conversion style techniques when using the full
target speaker corpus; with fewer adaptation data,
however, no significant listener preference for either
HMM adaptation or voice conversion methods was found.},
doi = {10.1109/TASL.2009.2035029},
issn = {1558-7916},
keywords = {HMM adaptation techniques;child speech
synthesis;hidden Markov model;speaker adaptive modeling
technique;speaker dependent technique;speaker-adaptive
voice;statistical parametric synthesizer;target speaker
corpus;voice conversion;hidden Markov models;speech
synthesis;},
month = jul,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2010/YamagishiJ_Synthesis\%20of\%20Child\%20Speech.pdf},
year = 2010
}
@inproceedings{ling2011a,
author = {Ling, Zhen-Hua and Richmond, Korin and Yamagishi,
Junichi},
title = {Feature-space transform tying in unified
acoustic-articulatory modelling of articulatory control
of {HMM}-based speech synthesis},
booktitle = {Proc. Interspeech},
pages = {117--120},
address = {Florence, Italy},
abstract = {In previous work, we have proposed a method to control
the characteristics of synthetic speech flexibly by
integrating articulatory features into hidden Markov
model (HMM) based parametric speech synthesis. A
unified acoustic-articulatory model was trained and a
piecewise linear transform was adopted to describe the
dependency between these two feature streams. The
transform matrices were trained for each HMM state and
were tied based on each state's context. In this paper,
an improved acoustic-articulatory modelling method is
proposed. A Gaussian mixture model (GMM) is introduced
to model the articulatory space and the cross-stream
transform matrices are trained for each Gaussian
mixture instead of context-dependently. This means the
dependency relationship can vary with the change of
articulatory features flexibly. Our results show this
method improves the effectiveness of control over vowel
quality by modifing articulatory trajectories without
degrading naturalness.},
categories = {speech synthesis, articulatory features, hidden Markov
model, Gaussian mixture model},
month = {August},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2011/IS110482.pdf},
year = 2011
}
@inproceedings{5947506,
author = {Hashimoto, K. and Yamagishi, J. and Byrne, W. and
King, S. and Tokuda, K.},
title = {An analysis of machine translation and speech
synthesis in speech-to-speech translation system},
booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2011
IEEE International Conference on},
pages = {5108--5111},
abstract = {This paper provides an analysis of the impacts of
machine translation and speech synthesis on
speech-to-speech translation systems. The
speech-to-speech translation system consists of three
components: speech recognition, machine translation and
speech synthesis. Many techniques for integration of
speech recognition and machine translation have been
proposed. However, speech synthesis has not yet been
considered. Therefore, in this paper, we focus on
machine translation and speech synthesis, and report a
subjective evaluation to analyze the impact of each
component. The results of these analyses show that the
naturalness and intelligibility of synthesized speech
are strongly affected by the fluency of the translated
sentences.},
doi = {10.1109/ICASSP.2011.5947506},
issn = {1520-6149},
keywords = {machine translation;speech recognition;speech
synthesis;speech-to-speech translation system;speech
recognition;speech synthesis;},
month = may,
year = 2011
}
@inproceedings{junichi:interspeech2010,
author = {Junichi Yamagishi and Oliver Watts and Simon King and
Bela Usabaev},
title = {Roles of the Average Voice in Speaker-adaptive
{HMM}-based Speech Synthesis},
booktitle = {{Proc. Interspeech}},
pages = {418--421},
address = {Makuhari, Japan},
abstract = {In speaker-adaptive HMM-based speech synthesis, there
are typically a few speakers for which the output
synthetic speech sounds worse than that of other
speakers, despite having the same amount of adaptation
data from within the same corpus. This paper
investigates these fluctuations in quality and
concludes that as mel-cepstral distance from the
average voice becomes larger, the MOS naturalness
scores generally become worse. Although this negative
correlation is not that strong, it suggests a way to
improve the training and adaptation strategies. We also
draw comparisons between our findings and the work of
other researchers regarding ``vocal attractiveness.''},
keywords = {speech synthesis, HMM, average voice, speaker
adaptation},
month = {September},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2010/IS100361.pdf},
year = 2010
}
@inproceedings{junichi:icassp2010,
author = {J. Yamagishi and S. King},
title = {Simple methods for improving speaker-similarity of
{HMM}-based speech synthesis},
booktitle = {{Proc. ICASSP 2010}},
address = {Dallas, Texas, USA},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2010/JunichiICASSP10.pdf},
year = 2010
}
@inproceedings{hts2007-icassp,
author = {Junichi Yamagishi and Takashi Nose and Heiga Zen and
Tomoki Toda and Keiichi Tokuda},
title = {Performance Evaluation of The Speaker-Independent
{HMM}-based Speech Synthesis System "{HTS}-2007" for
the {Blizzard Challenge 2007}},
booktitle = {Proc. ICASSP 2008},
pages = {3957--3960},
address = {Las Vegas, U.S.A},
abstract = {This paper describes a speaker-independent/adaptive
HMM-based speech synthesis system developed for the
Blizzard Challenge 2007. The new system, named
’¡ÈHTS-2007’¡É, employs speaker adaptation
(CSMAPLR+MAP), feature-space adaptive training,
mixed-gender modeling, and full-covariance modeling
using CSMAPLR transforms, in addition to several other
techniques that have proved effective in our previous
systems. Subjective evaluation results show that the
new system generates significantly better quality
synthetic speech than that of speaker-dependent
approaches with realistic amounts of speech data, and
that it bears comparison with speaker-dependent
approaches even when large amounts of speech data are
available.},
categories = {speech synthesis, HMM-based speech synthesis, HTS,
speaker adaptation, voice conversion, average voice},
doi = {10.1109/ICASSP.2008.4518520},
key = {hts2007-icassp},
month = apr,
year = 2008
}
@article{junichi:ieee2010,
author = {J. Yamagishi and B. Usabaev and S. King and O. Watts
and J. Dines and J. Tian and R. Hu and Y. Guan and K.
Oura and K. Tokuda and R. Karhila and M. Kurimo},
title = {Thousands of Voices for {HMM}-based Speech Synthesis
-- Analysis and Application of {TTS} Systems Built on
Various {ASR} Corpora},
journal = {IEEE Transactions on Audio, Speech and Language
Processing},
volume = 18,
number = 5,
pages = {984--1004},
abstract = {In conventional speech synthesis, large amounts of
phonetically balanced speech data recorded in highly
controlled recording studio environments are typically
required to build a voice. Although using such data is
a straightforward solution for high quality synthesis,
the number of voices available will always be limited,
because recording costs are high. On the other hand,
our recent experiments with HMM-based speech synthesis
systems have demonstrated that speaker-adaptive
HMM-based speech synthesis (which uses an ``average
voice model'' plus model adaptation) is robust to
non-ideal speech data that are recorded under various
conditions and with varying microphones, that are not
perfectly clean, and/or that lack phonetic balance.
This enables us to consider building high-quality
voices on ``non-TTS'' corpora such as ASR corpora.
Since ASR corpora generally include a large number of
speakers, this leads to the possibility of producing an
enormous number of voices automatically. In this paper,
we demonstrate the thousands of voices for HMM-based
speech synthesis that we have made from several popular
ASR corpora such as the Wall Street Journal (WSJ0,
WSJ1, and WSJCAM0), Resource Management, Globalphone,
and SPEECON databases. We also present the results of
associated analysis based on perceptual evaluation, and
discuss remaining issues.},
doi = {10.1109/TASL.2010.2045237},
keywords = {Automatic speech recognition (ASR), H Triple S (HTS),
SPEECON database, WSJ database, average voice, hidden
Markov model (HMM)-based speech synthesis, speaker
adaptation, speech synthesis, voice conversion},
month = jul,
year = 2010
}
@inproceedings{CassiaIS12,
author = {Valentini-Botinhao, C. and Yamagishi, J. and King, S.},
title = {{Mel cepstral coefficient modification based on the
Glimpse Proportion measure for improving the
intelligibility of {HMM}-generated synthetic speech in
noise}},
booktitle = {Proc. Interspeech},
address = {Portland, USA},
abstract = {We propose a method that modifies the Mel cepstral
coefficients of HMM-generated synthetic speech in order
to increase the intelligibility of the generated speech
when heard by a listener in the presence of a known
noise. This method is based on an approximation we
previously proposed for the Glimpse Proportion measure.
Here we show how to update the Mel cepstral
coefficients using this measure as an optimization
criterion and how to control the amount of distortion
by limiting the frequency resolution of the
modifications. To evaluate the method we built eight
different voices from normal read-text speech data from
a male speaker. Some voices were also built from
Lombard speech data produced by the same speaker.
Listening experiments with speech-shaped noise and with
a single competing talker indicate that our method
significantly improves intelligibility when compared to
unmodified synthetic speech. The voices built from
Lombard speech outperformed the proposed method
particularly for the competing talker case. However,
compared to a voice using only the spectral parameters
from Lombard speech, the proposed method obtains
similar or higher performance.},
categories = {HMM-based speech synthesis, intelligibility
enhancement, Mel cepstral coefficients},
month = {September},
year = 2012
}
@inproceedings{wester:ssw7:10,
author = {Mirjam Wester and John Dines and Matthew Gibson and
Hui Liang and Yi-Jian Wu and Lakshmi Saheer and Simon
King and Keiichiro Oura and Philip N. Garner and
William Byrne and Yong Guan and Teemu Hirsim\"{a}ki and
Reima Karhila and Mikko Kurimo and Matt Shannon and
Sayaka Shiota and Jilei Tian and Keiichi Tokuda and
Junichi Yamagishi},
title = {Speaker adaptation and the evaluation of speaker
similarity in the {EMIME} speech-to-speech translation
project},
booktitle = {Proc. of 7th ISCA Speech Synthesis Workshop},
address = {Kyoto, Japan},
abstract = {This paper provides an overview of speaker adaptation
research carried out in the EMIME speech-to-speech
translation (S2ST) project. We focus on how speaker
adaptation transforms can be learned from speech in one
language and applied to the acoustic models of another
language. The adaptation is transferred across
languages and/or from recognition models to synthesis
models. The various approaches investigated can all be
viewed as a process in which a mapping is defined in
terms of either acoustic model states or linguistic
units. The mapping is used to transfer either speech
data or adaptation transforms between the two models.
Because the success of speaker adaptation in
text-to-speech synthesis is measured by judging speaker
similarity, we also discuss issues concerning
evaluation of speaker similarity in an S2ST scenario.},
categories = {speaker adaptation, evaluation},
month = {September},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2010/wester_ssw7_2010.pdf},
year = 2010
}
@inproceedings{hts2008,
author = {Junichi Yamagishi and Heiga Zen and Yi-Jian Wu and
Tomoki Toda and Keiichi Tokuda},
title = {The {HTS}-2008 System: Yet Another Evaluation of the
Speaker-Adaptive {HMM}-based Speech Synthesis System in
The {2008 Blizzard Challenge}},
booktitle = {Proc. Blizzard Challenge 2008},
address = {Brisbane, Australia},
abstract = {For the 2008 Blizzard Challenge, we used the same
speaker-adaptive approach to HMM-based speech synthesis
that was used in the HTS entry to the 2007 challenge,
but an improved system was built in which the
multi-accented English average voice model was trained
on 41 hours of speech data with high-order mel-cepstral
analysis using an efficient forward-backward algorithm
for the HSMM. The listener evaluation scores for the
synthetic speech generated from this system was much
better than in 2007: the system had the equal best
naturalness on the small English data set and the equal
best intelligibility on both small and large data sets
for English, and had the equal best naturalness on the
Mandarin data. In fact, the English system was found to
be as intelligible as human speech.},
categories = {speech synthesis, HMM-based speech synthesis, HTS,
speaker adaptation, voice conversion, average voice,
Blizzard Challenge},
key = {hts2008},
month = sep,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/HTS2008.pdf},
year = 2008
}
@inproceedings{6287948,
author = {Saheer, L. and Yamagishi, J. and Garner, P.N. and
Dines, J.},
title = {Combining vocal tract length normalization with
hierarchial linear transformations},
booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2012
IEEE International Conference on},
volume = {},
number = {},
pages = {4493 -4496},
abstract = {Recent research has demonstrated the effectiveness of
vocal tract length normalization (VTLN) as a rapid
adaptation technique for statistical parametric speech
synthesis. VTLN produces speech with naturalness
preferable to that of MLLR-based adaptation techniques,
being much closer in quality to that generated by the
original average voice model. However with only a
single parameter, VTLN captures very few speaker
specific characteristics when compared to linear
transform based adaptation techniques. This paper
proposes that the merits of VTLN can be combined with
those of linear transform based adaptation in a
hierarchial Bayesian framework, where VTLN is used as
the prior information. A novel technique for
propagating the gender information from the VTLN prior
through constrained structural maximum a posteriori
linear regression (CSMAPLR) adaptation is presented.
Experiments show that the resulting transformation has
improved speech quality with better naturalness,
intelligibility and improved speaker similarity.},
doi = {10.1109/ICASSP.2012.6287948},
issn = {1520-6149},
keywords = {CSMAPLR adaptation;MLLR based adaptation
technique;constrained structural maximum a posteriori
linear regression;hierarchial Bayesian
framework;hierarchial linear
transformation;intelligibility;rapid adaptation
technique;speaker similarity;statistical parametric
speech synthesis;vocal tract length normalization;Bayes
methods;speech intelligibility;},
month = mar,
year = 2012
}
@inproceedings{jyamagis07:hts2007,
author = {Junichi Yamagishi and Heiga Zen and Tomoki Toda and
Keiichi Tokuda},
title = {Speaker-Independent {HMM}-based Speech Synthesis
System -- {HTS-2007} System for the {Blizzard Challenge
2007}},
booktitle = {Proc. Blizzard Challenge 2007},
abstract = {This paper describes an HMM-based speech synthesis
system developed by the HTS working group for the
Blizzard Challenge 2007. To further explore the
potential of HMM-based speech synthesis, we incorporate
new features in our conventional system which underpin
a speaker-independent approach: speaker adaptation
techniques; adaptive training for HSMMs; and full
covariance modeling using the CSMAPLR transforms.},
categories = {HMM, speech synthesis, speaker adaptation, HTS,
Blizzard Challenge},
month = aug,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2007/blizzard2007-HTS.pdf},
year = 2007
}
@inproceedings{michael:interspeech2010,
author = {Michael Pucher and Dietmar Schabus and Junichi
Yamagishi},
title = {Synthesis of fast speech with interpolation of adapted
{HSMMs} and its evaluation by blind and sighted
listeners},
booktitle = {Proc. Interspeech},
pages = {2186--2189},
address = {Makuhari, Japan},
abstract = {In this paper we evaluate a method for generating
synthetic speech at high speaking rates based on the
interpolation of hidden semi-Markov models (HSMMs)
trained on speech data recorded at normal and fast
speaking rates. The subjective evaluation was carried
out with both blind listeners, who are used to very
fast speaking rates, and sighted listeners. We show
that we can achieve a better intelligibility rate and
higher voice quality with this method compared to
standard HSMM-based duration modeling. We also evaluate
duration modeling with the interpolation of all the
acoustic features including not only duration but also
spectral and F0 models. An analysis of the mean squared
error (MSE) of standard HSMM-based duration modeling
for fast speech identifies problematic linguistic
contexts for duration modeling.},
keywords = {speech synthesis, fast speech, hidden semi- Markov
model},
month = {September},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2010/IS100294.pdf},
year = 2010
}
@inproceedings{richmond2007b,
author = {Richmond, K. and Strom, V. and Clark, R. and
Yamagishi, J. and Fitt, S.},
title = {Festival Multisyn Voices for the 2007 Blizzard
Challenge},
booktitle = {Proc. Blizzard Challenge Workshop (in Proc. SSW6)},
address = {Bonn, Germany},
abstract = {This paper describes selected aspects of the Festival
Multisyn entry to the Blizzard Challenge 2007. We
provide an overview of the process of building the
three required voices from the speech data provided.
This paper focuses on new features of Multisyn which
are currently under development and which have been
employed in the system used for this Blizzard
Challenge. These differences are the application of a
more flexible phonetic lattice representation during
forced alignment labelling and the use of a pitch
accent target cost component. Finally, we also examine
aspects of the speech data provided for this year's
Blizzard Challenge and raise certain issues for
discussion concerning the aim of comparing voices made
with differing subsets of the data provided.},
categories = {tts, blizzard, multisyn, unit selection},
key = {richmond2007b},
month = aug,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2007/blizzard2007paper.pdf},
year = 2007
}
@article{2012E121001,
author = {Junichi Yamagishi and Christophe Veaux and Simon King
and Steve Renals},
title = {Speech synthesis technologies for individuals with
vocal disabilities: Voice banking and reconstruction},
journal = {Acoustical Science and Technology},
volume = {33},
number = {1},
pages = {1--5},
url = {http://www.jstage.jst.go.jp/browse/ast/33/1/_contents},
year = 2012
}
@article{Creer2012,
author = {Sarah Creer and Stuart Cunningham and Phil Green and
Junichi Yamagishi},
title = {Building personalised synthetic voices for individuals
with severe speech impairment},
journal = {Computer Speech and Language},
volume = {},
number = {0},
pages = { - },
note = {},
abstract = {For individuals with severe speech impairment accurate
spoken communication can be difficult and require
considerable effort. Some may choose to use a voice
output communication aid (or VOCA) to support their
spoken communication needs. A VOCA typically takes
input from the user through a keyboard or switch-based
interface and produces spoken output using either
synthesised or recorded speech. The type and number of
synthetic voices that can be accessed with a VOCA is
often limited and this has been implicated as a factor
for rejection of the devices. Therefore, there is a
need to be able to provide voices that are more
appropriate and acceptable for users. This paper
reports on a study that utilises recent advances in
speech synthesis to produce personalised synthetic
voices for 3 speakers with mild to severe dysarthria,
one of the most common speech disorders. Using a
statistical parametric approach to synthesis, an
average voice trained on data from several unimpaired
speakers was adapted using recordings of the impaired
speech of 3 dysarthric speakers. By careful selection
of the speech data and the model parameters, several
exemplar voices were produced for each speaker. A
qualitative evaluation was conducted with the speakers
and listeners who were familiar with the speaker. The
evaluation showed that for one of the 3 speakers a
voice could be created which conveyed many of his
personal characteristics, such as regional identity,
sex and age.},
doi = {10.1016/j.csl.2012.10.001},
issn = {0885-2308},
keywords = {Speech synthesis, Augmentative and alternative
communication, Disordered speech, Voice output
communication aid},
url = {http://www.sciencedirect.com/science/article/pii/S0885230812000836?v=s5},
year = 2012
}
@inproceedings{jyamagis:1000sHTS,
author = {J. Yamagishi and Bela Usabaev and Simon King and
Oliver Watts and John Dines and Jilei Tian and Rile Hu
and Yong Guan and Keiichiro Oura and Keiichi Tokuda and
Reima Karhila and Mikko Kurimo},
title = {Thousands of voices for {HMM}-based speech synthesis},
booktitle = {Proc. Interspeech},
pages = {420--423},
address = {Brighton, U.K.},
abstract = {Our recent experiments with HMM-based speech synthesis
systems have demonstrated that speaker-adaptive
HMM-based speech synthesis (which uses an ‘average
voice model’ plus model adaptation) is robust to
non-ideal speech data that are recorded under various
conditions and with varying microphones, that are not
perfectly clean, and/or that lack of phonetic balance.
This enables us consider building high-quality voices
on ’non-TTS’ corpora such as ASR corpora. Since ASR
corpora generally include a large number of speakers,
this leads to the possibility of producing an enormous
number of voices automatically. In this paper we show
thousands of voices for HMM-based speech synthesis that
we have made from several popular ASR corpora such as
the Wall Street Journal databases (WSJ0/WSJ1/WSJCAM0),
Resource Management, Globalphone and Speecon. We report
some perceptual evaluation results and outline the
outstanding issues.},
month = sep,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2009/index.php},
year = 2009
}
@inproceedings{anderssonetal2010_ssw7,
author = {Sebastian Andersson and Junichi Yamagishi and Robert
Clark},
title = {Utilising Spontaneous Conversational Speech in
{HMM}-Based Speech Synthesis},
booktitle = {The 7th ISCA Tutorial and Research Workshop on Speech
Synthesis},
abstract = {Spontaneous conversational speech has many
characteristics that are currently not well modelled in
unit selection and HMM-based speech synthesis. But in
order to build synthetic voices more suitable for
interaction we need data that exhibits more
conversational characteristics than the generally used
read aloud sentences. In this paper we will show how
carefully selected utterances from a spontaneous
conversation was instrumental for building an HMM-based
synthetic voices with more natural sounding
conversational characteristics than a voice based on
carefully read aloud sentences. We also investigated a
style blending technique as a solution to the inherent
problem of phonetic coverage in spontaneous speech
data. But the lack of an appropriate representation of
spontaneous speech phenomena probably contributed to
results showing that we could not yet compete with the
speech quality achieved for grammatical sentences.},
categories = {HMM, speech synthesis, spontaneous speech,
conversation, lexical fillers, filled pauses},
month = sep,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2010/ssw7_paper.pdf},
year = 2010
}
@inproceedings{letter_based_TTS,
author = {Oliver Watts and Junichi Yamagishi and Simon King},
title = {Letter-based speech synthesis},
booktitle = {Proc. Speech Synthesis Workshop 2010},
pages = {317-322},
address = {Nara, Japan},
abstract = {Initial attempts at performing text-to-speech
conversion based on standard orthographic units are
presented, forming part of a larger scheme of training
TTS systems on features that can be trivially extracted
from text. We evaluate the possibility of using the
technique of decision-tree-based context clustering
conventionally used in HMM-based systems for
parametertying to handle letter-to-sound conversion. We
present the application of a method of compound-feature
discovery to corpusbased speech synthesis. Finally, an
evaluation of intelligibility of letter-based systems
and more conventional phoneme-based systems is
presented.},
month = sep,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2010/ssw7.pdf},
year = 2010
}
![[ intranet ]](/images/menu_intranet.png)
![[ festival ]](/images/menu_festival.png)