1997.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/1997-citations -ob /home/korin/projects/publications/new_output/transitdata/1997.bib -c 'year : "1997"' /home/korin/projects/publications/filtlists/full_publications_list.bib}}
@inproceedings{Williams_1997_a,
author = {Briony J. Williams and Stephen Isard},
title = {A keyvowel approach to the synthesis of regional
accents of {E}nglish},
booktitle = {Eurospeech 97},
address = {Rhodes, Greece},
categories = {synthesis},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Williams_1997_a.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Williams_1997_a.ps},
year = 1997
}
@inproceedings{fitt_eurospeech97,
author = {Sue Fitt},
title = {The generation of regional pronunciations of {E}nglish
for speech synthesis},
booktitle = {Proc. Eurospeech 1997},
address = {Rhodes, Greece},
abstract = {Most speech synthesisers and recognisers for English
currently use pronunciation lexicons in standard
British or American accents, but as use of speech
technology grows there will be more demand for the
incorporation of regional accents. This paper describes
the use of rules to transform existing lexicons of
standard British and American pronunciations to a set
of regional British and American accents. The paper
briefly discusses some features of the regional accents
in the project, and the framework used for generatiing
pronunciations. Certain theoretical and practical
problems are highlighted; for some of these, solutions
are suggested, but it is shown that some difficulties
cannot be resolved by automatic rules. However,
althought the method described cannot produce phonetic
transcriptions with 100\% accuracy, it is more accurate
than using letter-to-sound rules, and faster than
producing transcriptions by hand.},
categories = {speech synthesis, lexicon, accents, regional
pronunciation},
month = sep,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Fitt_1997_a.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Fitt_1997_a.ps},
year = 1997
}
@inproceedings{clark_gala97,
author = {Robert A. J. Clark},
title = {Language Acquisition and Implication for Language
Change: A Computational Model},
booktitle = {Proceedings of the {GALA} 97 Conference on Language
Acquisition},
pages = {322-326},
categories = {lm},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/clark_gala97.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/clark_gala97.ps},
year = 1997
}
@inproceedings{king:portele:hoefer:eurospeech1997,
author = {Simon King and Thomas Portele and Florian H\"ofer},
title = {Speech synthesis using non-uniform units in the
{V}erbmobil project},
booktitle = {Proc. {E}urospeech 97},
volume = 2,
pages = {569-572},
address = {Rhodes, Greece},
abstract = {We describe a concatenative speech synthesiser for
British English which uses the HADIFIX inventory
structure originally developed for German by Portele.
An inventory of non-uniform units was investigated with
the aim of improving segmental quality compared to
diphones. A combination of soft (diphone) and hard
concatenation was used, which allowed a dramatic
reduction in inventory size. We also present a unit
selection algorithm which selects an optimum sequence
of units from this inventory for a given phoneme
sequence. The work described is part of the
concept-to-speech synthesiser for the language and
speech project Verbmobil which is funded by the German
Ministry of Science (BMBF).},
categories = {},
month = sep,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/King_Portele_Hoefer_eurospeech1997.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/King_Portele_Hoefer_eurospeech1997.ps},
year = 1997
}
@inproceedings{kessens-CLS-97,
author = {J.M. Kessens and M. Wester},
title = {Improving Recognition Performance by Modelling
Pronunciation Variation},
booktitle = {Proc. of the CLS opening Academic Year '97 '98},
pages = {1-20},
address = {Nijmegen},
abstract = {This paper describes a method for improving the
performance of a continuous speech recognizer by
modelling pronunciation variation. Although the
improvements obtained with this method are small, they
are in line with those reported by other authors. A
series of experiments was carried out to model
pronunciation variation. In the first set of
experiments word internal pronunciation variation was
modelled by applying a set of four phonological rules
to the words in the lexicon. In the second set of
experiments, variation across word boundaries was also
modelled. The results obtained with both methods are
presented in detail. Furthermore, statistics are given
on the application of the four phonological rules on
the training database. We will explain why the
improvements obtained with this method are small and
how we intend to increase the improvements in our
future research.},
categories = {asr, pm, VIOS, Nijmegen},
pdf = {http://www.cstr.ed.ac.uk/downloads/publications/1997/kessens.1997.1.pdf},
year = 1997
}
@inproceedings{Shimodaira1997Eurospeech,
author = {Hiroshi Shimodaira and Mitsuru Nakai and Akihiro
Kumata},
title = {{Restration of Pitch Pattern of Speech Based on a
Pitch Gereration Model}},
booktitle = {Proc. EuroSpeech'97},
pages = {512--524},
abstract = { In this paper a model-based approach for restoring a
continuous fundamental frequency (F0) contour from the
noisy output of an F0 extractor is investigated. In
contrast to the conventional pitch trackers based on
numerical curve-fitting, the proposed method employs a
quantitative pitch generation model, which is often
used for synthesizing F0 contour from prosodic event
commands for estimating continuous F0 pattern. An
inverse filtering technique is introduced for obtaining
the initial candidates of the prosodic commands. In
order to find the optimal command sequence from the
commands efficiently, a beam-search algorithm and an
N-best technique are employed. Preliminary experiments
for a male speaker of the ATR B-set database showed
promising results both in quality of the restored
pattern and estimation of the prosodic events. },
categories = {f0, jaist},
month = sep,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/euro97.pdf},
year = 1997
}
@article{Hitzeman_1997_c,
author = {Janet Hitzeman},
title = {Semantic Partition and the Ambiguity of Temporal
Adverbials},
journal = {Journal of Natural Language Semantics},
volume = 5,
pages = {87-100},
categories = {syntax, semantics},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Hitzeman_1997_c.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Hitzeman_1997_c.ps},
year = 1997
}
@inproceedings{hennebert-eurospeech97,
author = {J.~Hennebert and C.~Ris and H.~Bourlard and S.~Renals
and N.~Morgan},
title = {Estimation of global posteriors and forward-backward
training of hybrid {HMM/ANN} systems},
booktitle = {Proc. Eurospeech},
pages = {1951--1954},
address = {Rhodes},
abstract = {The results of our research presented in this paper
are two-fold. First, an estimation of global
posteriors[5~5 is formalized in the framework of hybrid
HMM/ANN systems. It is shown that hybrid HMM/ANN
systems, in which the ANN part estimates local
posteriors can be used to model global posteriors. This
formalization provides us with a clear theory in which
both REMAP and ``classical'' Viterbi trained hybrid
systems are unified. Second, a new forward-backward
training of hybrid HMM/ANN systems is derived from the
previous formulation. Comparisons of performance
between Viterbi and forward-backward hybrid systems are
presented and discussed.},
categories = {sprach,am,hybrid,sheffield},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/eurosp97-remap.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/eurosp97-remap.ps.gz},
year = 1997
}
@inproceedings{Keeni1997ICDAR,
author = {Kanad Keeni and Hiroshi Shimodaira and Kenji Nakayama},
title = {{On Distributed Representation of Output Layer for
Recognizing Japanese Kana Characters Using Neural
Networks}},
booktitle = {Proceedings of the 4'th International Conference on
Document Analysis and Recognition, ICDAR'97},
pages = {600--603},
note = {Ulm, Germany},
categories = {hwr, ann, jaist},
month = jul,
year = 1997
}
@inproceedings{Huckvale_1997_a,
author = {M. Huckvale and C. Benoit and C. Bowerman and A.
Eriksson and M. Rosner and M. Tatham and Briony J.
Williams},
title = {Opportunities for Computer-Aided Instruction in
Phonetics and Speech Communication Provided by the
Internet},
booktitle = {Eurospeech 97},
address = {Rhodes, Greece},
categories = {phonetics, instruction},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Huckvale_1997_a.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Huckvale_1997_a.ps},
year = 1997
}
@article{Carletta_1997_b,
author = {Jean Carletta and Amy Isard and Stephen Isard and
Jacqueline C. Kowtko and Gwyneth Doherty-Sneddon and
Anne H. Anderson},
title = {The reliability of a dialogue structure coding scheme},
journal = {Computational Linguistics},
volume = 23,
number = 1,
pages = {13-31},
categories = {dialogue coding},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Carletta_1997_b.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Carletta_1997_b.ps},
year = 1997
}
@inproceedings{wester-97,
author = {M. Wester and J.M. Kessens and C. Cucchiarini and H.
Strik},
title = {Modelling pronunciation variation: some preliminary
results},
booktitle = {Proc. of the Dept. of Language & Speech},
pages = {127-137},
address = {Nijmegen},
abstract = {In this paper we describe a method for improving the
performance of a continuous speech recognizer by
modelling pronunciation variation. Although the results
obtained with this method are in line with those
reported by other authors, the magnitude of the
improvements is very small. In looking for possible
explanations for these results, we computed various
sorts of statistics about the material. Since these
data proved to be very useful in understanding the
effects of our method, they are discussed in this
paper. Moreover, on the basis of these statistics we
discuss how the system can be improved in the future.},
categories = {asr, pm, VIOS, Nijmegen},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/wester.1997.1.pdf},
year = 1997
}
@article{Hitzeman_1997_a,
author = {Janet Hitzeman and Chris Mellish and Jon Oberlander},
title = {Generation of Museum Web pages: The Intelligent
Labelling Explorer},
journal = {Archives and Museum Informatics},
volume = 11,
pages = {107-115},
categories = {nlg, ilex},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Hitzeman_1997_a.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Hitzeman_1997_a.ps},
year = 1997
}
@inproceedings{Black_1997_a,
author = {Alan W. Black and Paul A. Taylor},
title = {Assigning Phrase Breaks from Part-of-Speech Sequences},
booktitle = {Eurospeech97},
volume = 2,
pages = {995-998},
address = {Rhodes, Greece},
categories = {synthesis, phrasing, satissfy, festival},
key = {Black \& Taylor},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Black_1997_a.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Black_1997_a.ps},
year = 1997
}
@inproceedings{williams-eurospeech97,
author = {G.~Williams and S.~Renals},
title = {Confidence measures for hybrid {HMM/ANN} speech
recognition},
booktitle = {Proc. Eurospeech},
pages = {1955--1958},
address = {Rhodes},
abstract = {In this paper we introduce four acoustic confidence
measures which are derived from the output of a hybrid
HMM/ANN large vocabulary continuous speech recognition
system. These confidence measures, based on local
posterior probability estimates computed by an ANN, are
evaluated at both phone and word levels, using the
North American Business News corpus.},
categories = {recognition,conf,hybrid,wsj,sheffield},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/eurosp97-conf.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/eurosp97-conf.ps.gz},
year = 1997
}
@techreport{king:verbmobil1996a,
author = {Simon King},
title = {Final report for {V}erbmobil {T}eilprojekt 4.4},
institution = {IKP, Universität Bonn},
number = {ISSN 1434-8845},
note = {Verbmobil-Report 195 available at {\tt
http://verbmobil.dfki.de}},
abstract = {Final report for Verbmobil English speech synthesis},
categories = {},
month = jan,
year = 1997
}
@inproceedings{Bao1997-1,
author = {Tu Bao Ho and Nguyen Trong Dung and Hiroshi Shimodaira
and Masayuki Kimura},
title = {{An Interactive-Graphic Environment for Discovering
and Using Conceptual Knowledge}},
booktitle = {7th European-Japanese Conference on Information
Modelling and Knowledge Bases},
pages = {327--343},
categories = {kdd, jaist},
month = may,
year = 1997
}
@inproceedings{Lin97,
author = {Lincoln, M. and Cox, S.J. and Ringland, S.},
title = {A fast method of speaker normalisation using formant
estimation},
booktitle = {5th European Conference on Speech Communication and
Technology},
pages = {2095--2098},
address = {Rhodes},
abstract = {It has recently been shown that normalisation of vocal
tract length can significantly increase recognition
accuracy in speaker independent automatic speech
recognition systems. An inherent difficulty with this
technique is in automatically estimating the
normalisation parameter from a new speaker's speech and
previous techniques have typically relied on an
exhaustive search to estimate this parameter. In this
paper, we present a method of normalising utterances by
a linear warping of the mel filter bank channels in
which in which the normalisation parameter is estimated
by fitting formant estimates to a probabilistic model.
This method is fast, computitionally inexpensive and
requires only a limited amount of data for estimation.
It generates normalisations which are close to those
which would be found by an exhaustive search. The
normalisation is applied to a phoneme recognition task
using the TIMIT database and results show a useful
improvement over an un-normalised speaker independent
system.},
categories = {adaptation, vocal tract, speaker characteristics, BT,
UEA},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/lincoln-espeech-97.pdf},
year = 1997
}
@inproceedings{Sproat_1997_a,
author = {R. Sproat and Paul A. Taylor and M. Tanenblatt and Amy
Isard},
title = {A Markup Language for Text-to-Speech Synthesis},
booktitle = {Eurospeech 97},
categories = {synthesis, markup, sable},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Sproat_1997_a.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Sproat_1997_a.ps},
year = 1997
}
@inproceedings{Nakai1997Eurospeech,
author = {Mitsuru Nakai and Hiroshi Shimodaira},
title = {{On Representation of Fundamental Frequency of Speech
for Prosody Analysis Using Reliability Function}},
booktitle = {Proc. EuroSpeech'97},
pages = {243--246},
categories = {f0, jaist},
month = sep,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Nakai1997Eurospeech.pdf},
year = 1997
}
@inproceedings{gotoh-eurospeech97,
author = {Y.~Gotoh and S.~Renals},
title = {Document space models using latent semantic analysis},
booktitle = {Proc. Eurospeech},
pages = {1443--1446},
address = {Rhodes},
abstract = {In this paper, an approach for constructing mixture
language models (LMs) based on some notion of semantics
is discussed. To this end, a technique known as latent
semantic analysis (LSA) is used. The approach
encapsulates corpus-derived semantic information and is
able to model the varying style of the text. Using such
information, the corpus texts are clustered in an
unsupervised manner and mixture LMs are automatically
created. This work builds on previous work in the field
of information retrieval which was recently applied by
Bellegarda et. al. to the problem of clustering words
by semantic categories. The principal contribution of
this work is to characterize the document space
resulting from the LSA modeling and to demonstrate the
approach for mixture LM application. Comparison is made
between manual and automatic clustering in order to
elucidate how the semantic information is expressed in
the space. It is shown that, using semantic
information, mixture LMs performs better than a
conventional single LM with slight increase of
computational cost.},
categories = {sprach,lm,bnc,sheffield},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/eurosp97-lsa.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/eurosp97-lsa.ps.gz},
year = 1997
}
@inbook{Nakai1997Book,
author = {Mitsuru Nakai and Harald Singer and Yoshinori Sagisaka
and Hiroshi Shimodaira},
title = {{Accent Phrase Segmentation by F0 Clustering Using
Superpositional Modeling}},
pages = {343--360},
booktitle = {Computing Prosody, Chapter 22},
categories = {f0, atr, jaist},
month = jan,
year = 1997
}
@mastersthesis{richmond1997b,
author = {Richmond, K.},
title = {A Proposal for the Compartmental Modelling of Stellate
Cells in the Anteroventral Cochlear Nucleus, Using
Realistic Auditory Nerve Inputs},
school = {Centre for Cognitive Science, University of Edinburgh},
month = sep,
year = 1997
}
@inproceedings{Black_1997_b,
author = {Alan W. Black and Paul A. Taylor},
title = {Automatically Clustering Similar Units for Unit
Selection in Speech Synthesis},
booktitle = {Eurospeech97},
volume = 2,
pages = {601-604},
address = {Rhodes, Greece},
categories = {synthesis, waveform generation, unit selection,
festival, unisyn},
key = {Black \& Taylor},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Black_1997_b.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Black_1997_b.ps},
year = 1997
}
@inproceedings{Keeni1997ICPPOL,
author = {Kanad Keeni and Hiroshi Shimodaira},
title = {{On Representation of Output Layer for Recognizing
Japanese Kana Characters Using Neural Networks}},
booktitle = {Proc. the `17'th International Conference on Computer
Processing of Oriental Languages},
pages = {305--308},
note = {Baptist University, Kowloon Tong, Hong Kong},
categories = {ann, jaist},
month = apr,
year = 1997
}
@inproceedings{mayoaylettladd:97,
author = {Mayo, C. and Aylett, M. and Ladd, D. R.},
title = {Prosodic transcription of Glasgow English: an
evaluation study of {GlaToBI}},
booktitle = {Intonation: Theory, Models and Applications},
categories = {intonation, perceptual evaluation, Glasgow English,
transcription, ToBI},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/esca2.pdf},
year = 1997
}
@incollection{karlsen-casa97,
author = {B.~L.~Karlsen and G.~J.~Brown and M.~Cooke and
P.~Green and S.~Renals},
title = {Analysis of a simultaneous speaker sound corpus},
booktitle = {Computational Auditory Scene Analysis},
publisher = {Lawrence Erlbaum Associates},
editor = {D.~F.~Rosenthal and H.~G.~Okuno},
pages = {321--334},
categories = {},
year = 1997
}
@article{Kanno1997IEICE01,
author = {Sukeyasu Kanno and Hiroshi Shimodaira},
title = {{Voiced Sound Detection under Nonstationary and Heavy
Noisy Environment Using the Prediction Error of
Low-Frequency Spectrum}},
journal = {Trans. IEICE(D-II)},
volume = {J80-D-II},
number = {1},
pages = {26--35},
note = {(in Japanese)},
categories = {asr, jaist},
month = jan,
year = 1997
}
@techreport{Black_1997_e,
author = {Alan W. Black and Paul A. Taylor},
title = {The {F}estival {S}peech {S}ynthesis {S}ystem: System
Documentation},
institution = {{H}uman {C}ommunciation {R}esearch {C}entre,
{U}niversity of {E}dinburgh},
number = {HCRC/TR-83},
address = {Scotland, UK},
note = {Avaliable at
http://www.cstr.ed.ac.uk/projects/festival.html},
categories = {synthesis, systems, festival},
edition = {1.1},
key = {Black \& Taylor},
year = 1997
}
@inbook{Williams_1997_c,
author = {B Williams},
title = {Computer-Aided Learning and Use of the Internet:
Speech Sciences Education (section of chapter)},
booktitle = {The Landscape of Future Education in Speech
Communication Sciences: 1: Analysis},
categories = {teaching, phonetics, welshdata},
year = 1997
}
@inproceedings{Hockey_1997_a,
author = {Beth Ann Hockey and Deborah Rossen-Knill and Beverly
Spejewski and Matthew Stone and Stephen Isard},
title = {Can You Predict Responses to Yes/no Questions? Yes,
No, and Stuff},
booktitle = {Eurospeech '97},
pages = {2267-2270},
categories = {dialogue},
year = 1997
}
@inproceedings{Kowtko_1995,
author = {Jacqueline Kowtko},
title = {The Function of Intonation in Spontaneous and Read
Dialogue},
booktitle = {Proceedings of the XIIIth International Congress of
Phonetic Sciences},
volume = 2,
pages = {286-289},
address = {Stockholm, Sweden},
categories = {intonation, dialogue},
year = 1997
}
@inproceedings{Wright_1997_b,
author = {Helen Wright and Paul A. Taylor},
title = {Modelling Intonational Structure using Hidden Markov
Models},
booktitle = {ESCA workshop on Intonation: Theory Models and
Applications},
address = {Athens, Greece},
categories = {recognition, intonation, dialogue, id4s},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Wright_1997_b.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Wright_1997_b.ps},
year = 1997
}
@inproceedings{Dusterhoff_1997_a,
author = {Kurt Dusterhoff and Alan W. Black},
title = {Generating f0 contours for speech synthesis using the
tilt intonation theory},
booktitle = {Proc. ESCA Workshop on Intonation},
pages = {107-110},
address = {Athens, Greece.},
categories = {synthesis, intonation, festival},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Dusterhoff_1997_a.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Dusterhoff_1997_a.ps},
year = 1997
}
@inproceedings{strom97,
author = {V. Strom and A. Elsner and G. G{š}rz and W. Hess and
W. Kasper and A. Klein and H.U. Krieger and J. Spilker
and H. Weber},
title = {On the use of prosody in a speech-to-speech translator},
booktitle = {Proc. European Conf. on Speech Communication and
Technology},
address = {Rhodes},
abstract = {In this paper a speech-to-speech translator from
German to English is presented. Beside the traditional
processing steps it takes advantage of acoustically
detected prosodic phrase boundaries and focus. The
prosodic phrase boundaries reduce search space during
syntactic parsing and rule out analysis trees during
semantic parsing. The prosodic focus faciliates a
``shallow'' translation based on the best word chain in
cases where the deep analysis fails.},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/paper.eurospeech97.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/paper.eurospeech97.ps},
year = 1997
}
@inproceedings{Jurafsky_1997_c,
author = {Dan Jurafsky and A. Stolcke and E. Shriberg and R.
Bates and P. Taylor and K. Ries and N. Coccaro and R.
Martin and M. Meteer and C. Van Ess-Dykema},
title = {Automatic Detection of Discourse Structure for Speech
Recognition and Understanding.},
booktitle = {1997 IEEEWorkshop on Speech Recognition and
Understanding,},
address = {Santa Barbara},
categories = {prosody, recognition, language modelling, intonation,
dialogue, satissfy},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Jurafsky_1997_c.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Jurafsky_1997_c.ps},
year = 1997
}
@incollection{Black_1997_a1,
author = {Alan W. Black},
title = {Predicting The Intonation of Discourse Segments from
Examples in Dialogue Speech},
booktitle = {Computing Prosody},
publisher = {Springer-Verlag},
editor = {Sagisaka, Y. and Campbell, N. and Higuchi, N.},
pages = {117-128},
categories = {intonation, dialogue, chatr},
key = {Black},
year = 1997
}
@article{Nakai1997IEICE,
author = {Mitsuru Nakai and Harald Singer and Yoshimori Sagisaka
and Hiroshi Shimodaira},
title = {{Accent Phrase Segmentation Based on F0 Templates
Using a Superpositional Prosodic Model}},
journal = {Trans. IEICE (D-II)},
volume = {J80-D-II},
number = {10},
pages = {2605--2614},
note = {(in Japanese)},
categories = {jaist},
month = oct,
year = 1997
}
@inproceedings{kessens-COST-97,
author = {J.M. Kessens and M. Wester and C. Cucchiarini and H.
Strik},
title = {Testing a Method for Modelling Pronunciation Variation},
booktitle = {Proceedings of the COST workshop},
pages = {37-40},
address = {Rhodos},
abstract = {In this paper we describe a method for improving the
performance of a continuous speech recognizer by
modelling pronunciation variation. Although the results
obtained with this method are in line with those
reported by other authors, the magnitude of the
improvements is very small. In looking for possible
explanations for these results, we computed various
sorts of statistics about the material. Since these
data proved to be very useful in understanding the
effects of our method, they are discussed in this
paper. Moreover, on the basis of these statistics we
discuss how the system can be improved in the future.},
categories = {asr, pm, VIOS, Nijmegen},
pdf = {http://www.cstr.ed.ac.uk/downloads/publications/1997/kessens.1997.2.pdf},
year = 1997
}
@inproceedings{taylor:king:isard:wright:kowtko:eurospeech1997,
author = {Paul A. Taylor and Simon King and Stephen Isard and
Helen Wright and Jacqueline Kowtko},
title = {Using Intonation to Constrain Language Models in
Speech Recognition},
booktitle = {Proc. {E}urospeech'97},
address = {Rhodes},
abstract = {This paper describes a method for using intonation to
reduce word error rate in a speech recognition system
designed to recognise spontaneous dialogue speech. We
use a form of dialogue analysis based on the theory of
conversational games. Different move types under this
analysis conform to different language models.
Different move types are also characterised by
different intonational tunes. Our overall recognition
strategy is first to predict from intonation the type
of game move that a test utterance represents, and then
to use a bigram language model for that type of move
during recognition. point in a game.},
categories = {asr, intonation, dialogue, lm,id4s},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Taylor_King_Isard_Wright_Kowtko_eurospeech1997.pdf},
year = 1997
}
@inproceedings{richmond1997,
author = {Richmond, K. and Smith, A. and Amitay, E.},
title = {Detecting Subject Boundaries Within Text: A
Language-independent Statistical Approach},
booktitle = {Proc. The Second Conference on Empirical Methods in
Natural Language Processing},
pages = {47--54},
address = {Brown University, Providence, USA},
abstract = {We describe here an algorithm for detecting subject
boundaries within text based on a statistical lexical
similarity measure. Hearst has already tackled this
problem with good results (Hearst, 1994). One of her
main assumptions is that a change in subject is
accompanied by a change in vocabulary. Using this
assumption, but by introducing a new measure of word
significance, we have been able to build a robust and
reliable algorithm which exhibits improved accuracy
without sacrificing language independency.},
categories = {nlp, texttiling, subject detection},
key = {richmond1997},
month = aug,
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Richmond_1997_a.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Richmond_1997_a.ps},
year = 1997
}
@article{Taylor_1997_a,
author = {Paul A. Taylor and Amy Isard},
title = {{SSML}: A Speech Synthesis Markup Language},
journal = {Speech Communication},
number = 21,
pages = {123-133},
categories = {synthesis, markup, festival, sable},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Taylor_1997_a.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/Taylor_1997_a.ps},
year = 1997
}
@inbook{Williams_1997_d,
author = {B Williams},
title = {Spoken Language Corpus Representation (section of
chapter)},
publisher = {longmans},
booktitle = {Handbook of Standards and Resources for Spoken
Language Systems},
categories = {database},
year = 1997
}