1995.bib
@comment{{This file has been generated by bib2bib 1.92}}
@comment{{Command line: /home/korin/bibtex2html-1.92-LINUX/bib2bib -oc /home/korin/projects/publications/new_output/transitdata/1995-citations -ob /home/korin/projects/publications/new_output/transitdata/1995.bib -c 'year : "1995"' /home/korin/projects/publications/filtlists/full_publications_list.bib}}
@phdthesis{Forsyth_phd,
author = {Mark E. Forsyth},
title = {Semi-continuous hidden {M}arkov models for speaker
verification},
school = {University of Edinburgh},
categories = {verification},
year = 1995
}
@inproceedings{hochberg-arpa95,
author = {M.~Hochberg and G.~Cook and S.~Renals and T.~Robinson
and R.~Schechtman},
title = {The 1994 {Abbot} hybrid {connectionist--HMM} large
vocabulary recognition system},
booktitle = {Proc. ARPA Spoken Language Technology Workshop},
pages = {170--175},
categories = {wernicke,recognition,wsj,am,hybrid,abbot,eval,search,sheffield,cambridge},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/slt95.ps.gz},
year = 1995
}
@incollection{Carletta_1995_a,
author = {Jean Carletta and Amy Isard and Stephen Isard and
Jacqueline Kowtko and Gwyneth Doherty-Sneddon and Anne
H. Anderson},
title = {The Coding of Dialogue Structure in a Corpus},
booktitle = {Proceedings of the Ninth Twente Workshop on Language
Technology: Corpus-based Approaches to Dialogue
Modelling},
publisher = {Universiteit Twente, Enschede},
editor = {J.A. Andernach and S.P. van de Burgt and G.F. van der
Hoeven},
categories = {dialogue},
year = 1995
}
@inproceedings{isard:king:taylor:kowtko:snowbird95,
author = {Stephen Isard and Simon King and Paul A. Taylor and
Jacqueline Kowtko},
title = {Prosodic Information in a Speech Recognition System
intended for Dialogue},
booktitle = {IEEE Workshop in speech recognition},
address = {Snowbird, Utah},
abstract = {We report on an automatic speech recognition system
intended for use in dialogue, whose original aspect is
its use of prosodic information for two different
purposes. The first is to improve the word level
accuracy of the system. The second is to constrain the
language model applied to a given utterance by taking
into account the way that dialogue context and
intonational tune interact to limit the possibilities
for what an utterance might be.},
categories = {},
year = 1995
}
@inproceedings{Black_1995_c,
author = {Alan W. Black},
title = {Comparison of algorithms for predicting accent
placement in {E}nglish speech synthesis},
booktitle = {Proceedings of the Acoustics Society of Japan},
pages = {275-276},
categories = {synthesis, intonation, chatr},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Black_1995_c.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Black_1995_c.ps},
year = 1995
}
@inproceedings{Williams_1995_a,
author = {Briony J. Williams},
title = {Text-to-speech synthesis for {W}elsh and {W}elsh
{E}nglish},
booktitle = {Proc. Eurospeech '95, Madrid},
categories = {welsh, synthesis},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Williams_1995_a.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Williams_1995_a.ps},
year = 1995
}
@inproceedings{Taylor_1995_a,
author = {Paul A. Taylor},
title = {Using Neural Networks to Locate Pitch Accents},
booktitle = {Proc. Eurospeech '95, Madrid},
categories = {recognition, intonation, id4s},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Taylor_1995_a.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Taylor_1995_a.ps},
year = 1995
}
@inproceedings{robinson-icassp95,
author = {T.~Robinson and J.~Fransen and D.~Pye and J.~Foote and
S.~Renals},
title = {{WSJCAM0}: A {British English} speech corpus for large
vocabulary continuous speech recognition},
booktitle = {Proc IEEE ICASSP},
pages = {81--84},
address = {Detroit},
categories = {},
year = 1995
}
@inproceedings{Nakai1995ICASSP,
author = {Mitsuru Nakai and Singer Harald and Yoshinori Sagisaka
and Hiroshi Shimodaira},
title = {{Automatic Prosodic Segmentation by F0 Clustering
Using Superpositional Modeling}},
booktitle = {Proc. ICASSP-95, PR08.6},
pages = {624--627},
categories = {F0, atr, jaist},
journal = {},
month = may,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Nakai1995ICASSP.pdf},
year = 1995
}
@inproceedings{Koba1995HCIb,
author = {Hisao Koba and hiroshi Shimodaira and Masayuki Kimura},
title = {{Intelligent Automatic Document Transcription System
for Braille: To Improve Accessibility to Printed Matter
for the Visually Impaired}},
booktitle = {HIC International'95},
month = jul,
year = 1995
}
@inproceedings{Taylor_1995_c,
author = {Paul A. Taylor and Amy Isard},
title = {{SSML}: A Speech Synthesis Markup Language},
booktitle = {2nd Speak! Workshop: Speech Generation in Multimodal
Information Systems and Practical Applications,
Darmstadt},
categories = {synthesis, markup, festival, sable},
year = 1995
}
@inproceedings{Wrench_1995_b,
author = {Alan A. Wrench and M. S. Jackson and D. S. Soutar and
A.G. Robertson and J. Mackenzie Beck},
title = {Evaluation of a System for Segmental Speech Quality
Assessment: Voiceless Fricavties},
booktitle = {Proc. Eurospeech '95, Madrid},
categories = {},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Wrench_1995_b.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Wrench_1995_b.ps},
year = 1995
}
@inproceedings{Black_1995_a,
author = {Alan W. Black and N. Campbell},
title = {Predicting the Intonation of Discourse Segments from
Examples in Dialogue Speech},
booktitle = {E{SCA} workshop on spoken dialogue systems},
pages = {197-200},
address = {Denmark},
categories = {synthesis, intonation, chatr},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Black_1995_a.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Black_1995_a.ps},
year = 1995
}
@inproceedings{Black_1995_b,
author = {Alan W. Black and N. Campbell},
title = {Optimising Selection of Units from Speech Databases
for Concatenative Synthesis},
booktitle = {Eurospeech95},
volume = 1,
pages = {581-584},
address = {Madrid, Spain},
categories = {synthesis, waveform generation, unit selection, chatr},
key = {Black \& Campbell},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Black_1995_b.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Black_1995_b.ps},
year = 1995
}
@techreport{Williams_1995_b,
author = {Briony Williams},
title = {The Segmentation and Labelling of Speech Databases},
categories = {database, phonetics},
journal = {Edinburgh Occasional Papers in Linguistics},
volume = {eopl-95-3},
year = 1995
}
@inproceedings{Hitzeman_1995_a,
author = {Janet Hitzeman and Marc Moens and Claire Grover},
title = {Algorithms for analysing the Temporal Structure of
Discourse},
booktitle = {Proceedings of the Sixth International Conference of
the European Chapter of the Association for
Computational Linguistics},
address = {Dublin, Ireland},
categories = {text analysis},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Hitzeman_1995_a.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Hitzeman_1995_a.ps},
year = 1995
}
@mastersthesis{Isard_A_masters,
author = {Amy C. Isard},
title = {S{SML}: a markup language for speech synthesis},
school = {University of Edinburgh},
categories = {synthesis, markup, sable},
year = 1995
}
@inproceedings{renals-icassp95,
author = {S.~Renals and M.~Hochberg},
title = {Efficient search using posterior phone probability
estimates},
booktitle = {Proc IEEE ICASSP},
pages = {596--599},
address = {Detroit},
abstract = {In this paper we present a novel, efficient search
strategy for large vocabulary continuous speech
recognition (LVCSR). The search algorithm, based on
stack decoding, uses posterior phone probability
estimates to substantially increase its efficiency with
minimal effect on accuracy. In particular, the search
space is dramatically reduced by phone deactivation
pruning where phones with a small local posterior
probability are deactivated. This approach is
particularly well-suited to hybrid connectionist/hidden
Markov model systems because posterior phone
probabilities are directly computed by the acoustic
model. On large vocabulary tasks, using a trigram
language model, this increased the search speed by an
order of magnitude, with 2\% or less relative search
error. Results from a hybrid system are presented using
the Wall Street Journal LVCSR database for a 20,000
word task using a backed-off trigram language model.
For this task, our single-pass decoder took around 15
times realtime on an HP735 workstation. At the cost of
7\% relative search error, decoding time can be speeded
up to approximately realtime.},
categories = {wernicke,recognition,wsj,search,sheffield,cambridge},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/icassp95-search.ps.gz},
year = 1995
}
@inproceedings{neto-eurospeech95,
author = {J.~Neto and L.~Almeida and M.~Hochberg and C.~Martins
and L.~Nunes and S.~Renals and T.~Robinson},
title = {Speaker adaptation for hybrid {HMM--ANN} continuous
speech recogniton system},
booktitle = {Proc. Eurospeech},
pages = {2171--2174},
address = {Madrid},
abstract = {It is well known that recognition performance degrades
significantly when moving from a speaker- dependent to
a speaker-independent system. Traditional hidden Markov
model (HMM) systems have successfully applied
speaker-adaptation approaches to reduce this
degradation. In this paper we present and evaluate some
techniques for speaker-adaptation of a hybrid
HMM-artificial neural network (ANN) continuous speech
recognition system. These techniques are applied to a
well trained, speaker-independent, hybrid HMM-ANN
system and the recognizer parameters are adapted to a
new speaker through off-line procedures. The techniques
are evaluated on the DARPA RM corpus using varying
amounts of adaptation material and different ANN
architectures. The results show that speaker-adaptation
within the hybrid framework can substantially improve
system performance.},
categories = {wernicke,rm,recognition,am,hybrid,adaptation,sheffield,cambridge},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/eurosp95.ps.gz},
year = 1995
}
@inproceedings{Wrench_1995,
author = {Alan A. Wrench},
title = {Analysis of Fricatives Using Multiple Centres of
Gravity},
booktitle = {Proc. Eurospeech '95, Madrid},
categories = {},
year = 1995
}
@mastersthesis{sanders_masters,
author = {E. Sanders},
title = {Using Probabilistic Methods to Detect Phrase
Boundaries for Speech Synthesis},
school = {University of Edinburgh},
categories = {},
year = 1995
}
@incollection{ATR-Buch,
author = {W. Hess and A. Batliner and A. Kießling and R. Kompe
and E. N{š}th and A. Petzold and M. Reyelt and V. Strom},
title = {Prosodic Modules for Speech Recognition and
Understanding in {VERBMOBIL}},
booktitle = {Computing Prosody},
publisher = {Springer-Verlag},
editor = {Yoshinori Sagisaka, Nick Campbell, Norio Higuchi},
pages = {Part IV, Chapter 23, pp. 363 - 383},
address = {New York},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/hess_et_al.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/hess_et_al.ps},
year = 1995
}
@article{Taylor_1995_b,
author = {Paul A. Taylor},
title = {The Rise/Fall/Connection Model of Intonation},
journal = {Speech Communication},
volume = 15,
pages = {169-186},
categories = {synthesis, intonation},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Taylor_1995_b.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Taylor_1995_b.ps},
year = 1995
}
@inproceedings{Black_1995_d,
author = {Alan W. Black},
title = {Predicting the Intonation of Discourse Segments from
Examples in Dialogue Speech},
booktitle = {A{TR} workshop on computational modeling of prosody
for spontaneous speech processing},
address = {ATR, Japan},
categories = {synthesis, intonation, chatr},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Black_1995_d.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Black_1995_d.ps},
year = 1995
}
@inproceedings{Sanders_1995_b,
author = {Eric Sanders and Paul A. Taylor},
title = {Using Statistical Models to Predict Phrase Boundaries
for Speech Synthesis},
booktitle = {Proc. Eurospeech '95, Madrid},
categories = {synthesis, phrasing},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Sanders_1995_b.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Sanders_1995_b.ps},
year = 1995
}
@inproceedings{hochberg-icassp95,
author = {M.~Hochberg and S.~Renals and T.~Robinson and G.~Cook},
title = {Recent improvements to the {Abbot} large vocabulary
{CSR} system},
booktitle = {Proc IEEE ICASSP},
pages = {69--72},
address = {Detroit},
abstract = {ABBOT is the hybrid connectionist-hidden Markov model
(HMM) large-vocabulary continuous speech recognition
(CSR) system developed at Cambridge University. This
system uses a recurrent network to estimate the
acoustic observation probabilities within an HMM
framework. A major advantage of this approach is that
good performance is achieved using context-independent
acoustic models and requiring many fewer parameters
than comparable HMM systems. This paper presents
substantial performance improvements gained from new
approaches to connectionist model combination and
phone-duration modeling. Additional capability has also
been achieved by extending the decoder to handle larger
vocabulary tasks (20,000 words and greater) with a
trigram language model. This paper describes the recent
modifications to the system and experimental results
are reported for various test and development sets from
the November 1992, 1993, and 1994 ARPA evaluations of
spoken language systems.},
categories = {wernicke,recognition,wsj,am,hybrid,abbot,eval,search,sheffield,cambridge},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/icassp95-abbot.ps.gz},
year = 1995
}
@article{Forsyth_1995,
author = {Mark E. Forsyth},
title = {Discriminating observation probability ({DOP}) {HMM}
for speaker verification},
journal = {Speech Communication},
volume = 17,
pages = {117-129},
categories = {verification},
year = 1995
}
@inproceedings{strom95,
author = {V.~Strom},
title = {Detection of accents, phrase boundaries and sentence
modality in {G}erman with prosodic features},
booktitle = {Proc. European Conf. on Speech Communication and
Technology},
volume = {3},
pages = {2039-2041},
address = {Madrid},
abstract = {In this paper detectors for accents, phrase
boundaries, and sentence modality are described which
derive prosodic features only from the speech signal
and its fundamental frequency to support other modules
of a speech understanding system in an early analysis
stage, or in cases where no word hypotheses are
available. A new method for interpolating and
decomposing the fundamental frequency is suggested. The
detectors' underlying Gaussian distribution classifiers
were trained and tested with approximately 50 minutes
of spontaneous speech, yielding recognition rates of 78
percent for accents, 81 percent for phrase boundaries,
and 85 percent for sentence modality.},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/paper.eurospeech95.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/paper.eurospeech95.ps},
year = 1995
}
@inproceedings{Koba1995HCIa,
author = { and Hiroshi Shimodaira},
title = {{HI Design Based on the Costs of Human
Information-processing Model}},
booktitle = {HIC international'95},
pages = {},
categories = {HI, jaist},
month = jul,
year = 1995
}
@inproceedings{fitt_eurospeech95,
author = {Sue Fitt},
title = {The pronunciation of unfamiliar native and non-native
town names},
booktitle = {Proc. Eurospeech 1995},
address = {Madrid, Spain},
abstract = {This paper will discuss pronunciations of unfamiliar
names, both British and foreign, by native speakers of
English. Most studies which look at peoples'
pronunciations of unfamiliar of pseudowords are based
on English word-patterns, rather than a cross-language
selection, while algorithms for determining the
pronunciation of names from a variety of languages do
not necessarily tell us how real people behave in such
a situation. This paper shows that subjects may use
different systems or sub-systems of rules to pronounce
unknown names which they perceive to be non-native. If
we wish to model human behaviour in novel word
pronunciation, we need to take account the fact that,
while native speakers are not experts in all foreign
languages, neither are they linguistically naive.},
categories = {pronunciation, onomastics, names, phonology,
pseudowords, L2},
month = sep,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Fitt_1995_a.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1995/Fitt_1995_a.ps},
year = 1995
}