1996.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/1996-citations -ob /home/korin/projects/publications/new_output/transitdata/1996.bib -c 'year : "1996"' /home/korin/projects/publications/filtlists/full_publications_list.bib}}
@inproceedings{Hunt_1996_a,
author = {Andrew Hunt and Alan W. Black},
title = {Unit Selection in a Concatenative Speech Synthesis
System Using a Large Speech Database},
booktitle = {ICASSP-96},
volume = 1,
pages = {373-376},
address = {Atlanta, Georgia},
categories = {synthesis, waveform generation, unit selection, chatr},
key = {Hunt \& Black},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1996/Hunt_1996_a.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1996/Hunt_1996_a.ps},
year = 1996
}
@book{Knowles_1996_a,
author = {G Knowles and L. Taylor and B. Williams},
title = {A corpus of formal {B}ritish {E}nglish speech},
categories = {database},
year = 1996
}
@article{Keeni1996IEICE,
author = {Kanad Keeni and Hiroshi Shimodaira and Tetsuro Nishino
and Yasuo Tan},
title = {{Recognition of Devanagari Characters Using Neural
Networks}},
journal = {IEICE},
volume = {E79-D},
number = {5},
pages = {523--528},
categories = {character-recognition, ann, jaist},
month = may,
year = 1996
}
@mastersthesis{Dusterhoff_1996_b,
author = {K. Dusterhoff},
title = {Intone: A prototype intonation analysis system},
school = {Georgetown University},
categories = {intonation, automatic analysis},
year = 1996
}
@article{renals-splett96,
author = {S.~Renals},
title = {Phone deactivation pruning in large vocabulary
continuous speech recognition},
journal = {IEEE Signal Processing Letters},
volume = {3},
pages = {4--6},
abstract = {In this letter we introduce a new pruning strategy for
large vocabulary continuous speech recognition based on
direct estimates of local posterior phone
probabilities. This approach is well suited to hybrid
connectionist/hidden Markov model systems. Experiments
on the Wall Street Journal task using a 20,000 word
vocabulary and a trigram language model have
demonstrated that phone deactivation pruning can
increase the speed of recognition-time search by up to
a factor of 10, with a relative increase in error rate
of less than 2\%.},
categories = {wernicke,sprach,recognition,search,wsj,sheffield},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1996/splett96.ps.gz},
year = 1996
}
@incollection{Williams_1996_a,
author = {Briony J. Williams},
title = {The Status of Corpora as Linguistic Data},
booktitle = {Working with Speech},
publisher = {London: Longmans},
editor = {G. Knowles, A. Wichmann \& P. Alderson},
categories = {database},
year = 1996
}
@incollection{Williams_1996_d,
author = {B. Pickering and Briony J. Williams and G. Knowles},
title = {Analysis of Transcriber Differences in the SEC},
booktitle = {Working with Speech},
categories = {intonation, synthesis},
year = 1996
}
@inproceedings{taylor:shimodaira:isard:king:kowtko:icslp1996,
author = {Paul A. Taylor and Hiroshi Shimodaira and Stephen
Isard and Simon King and Jacqueline Kowtko},
title = {Using Prosodic Information to Constrain Language
Models for Spoken dialogue},
booktitle = {Proc. {ICSLP} `96},
address = {Philadelphia},
abstract = {We present work intended to improve speech recognition
performance for computer dialogue by taking into
account the way that dialogue context and intonational
tune interact to limit the possibilities for what an
utterance might be. We report here on the extra
constraint achieved in a bigram language model
expressed in terms of entropy by using separate
submodels for different sorts of dialogue acts and
trying to predict which submodel to apply by analysis
of the intonation of the sentence being recognised.},
categories = {asr, intonation, dialogue, lm,id4s},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1996/Taylor_1996_a.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1996/Taylor_1996_a.ps},
year = 1996
}
@inproceedings{Black_1996_c,
author = {N. Campbell and Alan W. Black},
title = {C{HATR}: a multi-lingual speech re-sequencing
synthesis system},
booktitle = {Institute of Electronic, Information and Communication
Engineers},
address = {Tokyo},
categories = {synthesis, unit selection, chatr},
year = 1996
}
@mastersthesis{McKenna_1996_a,
author = {John McKenna},
title = {Tone and INITIAL/FINAL Recognition for Mandarin
Chinese},
school = {University of Edinburgh},
categories = {},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1996/McKenna_1996_a.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1996/McKenna_1996_a.ps},
year = 1996
}
@mastersthesis{clark_msc96,
author = {Robert A.J. Clark},
title = {Internal and External Factors Affecting Language
Change: A Computational Model},
school = {University of Edinburgh},
categories = {lm},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1996/clark_msc96.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1996/clark_msc96.ps},
year = 1996
}
@inproceedings{fitt_icos96,
author = {Sue Fitt},
title = {Spelling unfamiliar names},
booktitle = {Proc. International Congress of Onomastic Sciences
1996},
abstract = {This paper will examine the written transcription of
unfamiliar spoken names. It is well documented that the
writing of personal and place names by people who are
unfamiliar with the spelling of the name contributes to
the evolution of names. The current paper describes a
study which examines the processes involved, using
experiments in which Scottish subjects are asked to
write down unfamiliar spoken British and European town
names.},
categories = {names, onomastics, orthography, phonology},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1996/Fitt_1996_a.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1996/Fitt_1996_a.ps},
year = 1996
}
@inproceedings{kershaw-icslp96,
author = {D.~Kershaw and T.~Robinson and S.~Renals},
title = {The 1995 {Abbot} {LVCSR} system for multiple unknown
microphones},
booktitle = {Proc. ICSLP},
pages = {1325-1328},
address = {Philadelphia PA},
categories = {wernicke,sprach,wsj,recognition,am,hybrid,abbot,search,eval,sheffield},
year = 1996
}
@incollection{Williams_1996_c,
author = {Briony J. Williams and P. Alderson},
title = {Synthesising {B}ritish {E}nglish intonation},
booktitle = {Working with Speech},
categories = {intonation, synthesis},
year = 1996
}
@inproceedings{Black_1996_b,
author = {Alan W. Black and Andrew Hunt},
title = {Generating F0 Contours from {ToBI} Labels Using Linear
Regression},
booktitle = {ICSLP96},
volume = 3,
pages = {1385-1388},
address = {Philadelphia, PA.},
categories = {synthesis, intonation, chatr},
key = {Black \& Hunt},
year = 1996
}
@manual{king:verbmobil1996c,
title = {Users {M}anual for {V}erbmobil {T}eilprojekt 4.4},
author = {Simon King},
organization = {IKP, Universität Bonn},
abstract = {Verbmobil English synthesiser users manual},
categories = {},
month = oct,
year = 1996
}
@incollection{Williams_1996_b,
author = {Briony J. Williams},
title = {The formulation of an intonation transcription system
for {B}ritish {E}nglish},
booktitle = {Working with Speech},
publisher = {London: Longmans},
editor = {G. Knowles, A. Wichmann \& P. Alderson},
categories = {intonation},
year = 1996
}
@incollection{robinson-yellowbook96,
author = {T.~Robinson and M.~Hochberg and S.~Renals},
title = {The use of recurrent networks in continuous speech
recognition},
booktitle = {Automatic Speech and Speaker Recognition -- Advanced
Topics},
publisher = {Kluwer Academic Publishers},
editor = {C.-H.~Lee and K.~K.~Paliwal and F.~K.~Soong},
pages = {233--258},
abstract = {This chapter describes a use of recurrent neural
networks (ie, feedback is incorporated in the
computation) as an acoustic model for continuous speech
recognition. The form of the recurrent neural network
is described, along with an appropriate parameter
estimation procedure. For each frame of acoustic data,
the recurrent network generates an estimate of the
posterior probability of the possible phones given the
observed acoustic signal. The posteriors are then
converted into scaled likelihoods and used as the
observation probabilities within a conventional
decoding paradigm (eg, Viterbi decoding). The
advantages of the using recurrent networks are that
they require a small number of parameters and provide a
fast decoding capability (relative to conventional
large vocabulary HMM systems).},
categories = {wernicke,sprach,wsj,recognition,am,hybrid,abbot,search,sheffield},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1996/rnn4csr96.ps.gz},
year = 1996
}
@inproceedings{renals-icassp96,
author = {S.~Renals and M.~Hochberg},
title = {Efficient evaluation of the {LVCSR} search space using
the {NOWAY} decoder},
booktitle = {Proc IEEE ICASSP},
pages = {149--152},
address = {Atlanta},
abstract = {This work further develops and analyses the large
vocabulary continuous speech recognition search
strategy reported at ICASSP-95. In particular, the
posterior-based phone deactivation pruning approach has
been extended to include phone-dependent thresholds and
an improved estimate of the least upper bound on the
utterance log-probability has been developed. Analysis
of the pruning procedures and of the search's
interaction with the language model has also been
performed. Experiments were carried out using the ARPA
North American Business News task with a 20,000 word
vocabulary and a trigram language model. As a result of
these improvements and analyses, the computational cost
of the recognition process performed by the Noway
decoder has been substantially reduced.},
categories = {wernicke,sprach,recognition,wsj,search,sheffield},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1996/icassp96.ps.gz},
year = 1996
}
@inproceedings{kershaw-arpa96,
author = {D.~Kershaw and T.~Robinson and S.~Renals},
title = {The 1995 {Abbot} hybrid {connectionist--HMM} large
vocabulary recognition system},
booktitle = {Proc. ARPA Spoken Language Technology Conference},
pages = {93--99},
categories = {wernicke,sprach,wsj,recognition,am,hybrid,abbot,search,eval,sheffield},
year = 1996
}
@techreport{king:verbmobil1996b,
author = {Simon King},
title = {Inventory design for {V}erbmobil {T}eilprojekt 4.4},
institution = {IKP, Universität Bonn},
abstract = {Inventory design for Verbmobil English speech
synthesis},
categories = {},
month = oct,
year = 1996
}
@phdthesis{Kowtko_1996_a,
author = {Jacqueline Kowtko},
title = {The Function of Intonation in Task-Oriented Dialogue},
categories = {prosody, intonation, dialogue, id4s},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1996/Kowtko_1996_a.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1996/Kowtko_1996_a.ps},
year = 1996
}
@incollection{Campbell_1996_a,
author = {N. Campbell and Alan W. Black},
title = {Prosody and the Selection of Source Units for
Concatenative Synthesis},
booktitle = {Progress in Speech Synthesis},
publisher = {Springer Verlag},
editor = {van Santen, J. and Sproat, R. and Olive, J. and
Hirschberg, J.},
pages = {279-282},
categories = {synthesis, intonation, waveform generation, unit
selection, chatr},
key = {Campbell \& Black},
year = 1996
}
@inproceedings{Dusterhoff_1996_a,
author = {K. Dusterhoff},
title = {Using computational analysis to determine pitch accent},
booktitle = {Proceedings Computational Linguistics in Montreal},
pages = {1-4},
categories = {intonation, automatic analysis},
year = 1996
}
@incollection{Isard_S_1996,
author = {A. Conkie and Stephen D. Isard},
title = {Optimal Coupling of Diphones},
booktitle = {Progress in Speech Synthesis},
publisher = {Springer},
editor = {Santen, J. P. H. and Sproat, R. W. and Olive, J. P.
and Hirschberg},
categories = {synthesis, waveform generation},
year = 1996
}
@inproceedings{strom96b,
author = {V. Strom and C. Widera},
title = {What's in the ``pure'' prosody?},
booktitle = {Proc. ICSLP},
address = {Philadelphia},
abstract = {Detectors for accents and phrase boundaries have been
developed which derive prosodic features 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. The detectors' underlying
Gaussian distribution classifiers were trained with 50
minutes and tested with 30 minutes of spontaneous
speech, yielding recognition rates of 74\% for accents
and 86\% for phrase boundaries. Since this material was
prosodically hand labelled, the question was, which
labels for phrase boundaries and accentuation were only
guided by syntactic or semantic knowledge, and which
ones are really prosodically marked. Therefore a small
test subset has been resynthesized in such a way that
comprehensibility was lost, but the prosodic
characteristics were kept. This subset has been
re-labelled by 11 listeners with nearly the same
accuracy as the detectors.},
pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1996/paper.icslp96.pdf},
ps = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1996/paper.icslp96.ps},
year = 1996
}