Stéphane Dupont
Faculté Polytechnique de Mons, TCTS Lab
[1]
H. Bourlard, S. Dupont, H. Hermansky, and N. Morgan.
Towards sub-band-based speech recognition.
In Proc. of European Signal Processing Conference, pages
1579-1582, Trieste, Italy, September 1996.
[ bib |
www ]
[2]
H. Bourlard and S. Dupont.
A new ASR approach based on independent processing and
recombination of partial frequency bands.
In Proc. of Intl. Conf. on Spoken Language Processing, pages
422-425, Philadelphia, October 1996.
[ bib |
www ]
[3]
S. Dupont and H. Bourlard.
Multiband approach for speech recognition.
In Proc. of ProRISC/IEEE Workshop on Circuits, Systems and
Signal Proc., pages 113-118, Mierlo, The Netherlands, November 1996.
[ bib |
www ]
[4]
Hervé Bourlard, Stéphane Dupont, and Christophe Ris.
Multi-stream speech recognition.
CC-AI Journal, special issue on prosody, 1997.
[ bib ]
[5]
Stéphane Dupont, Hervé Bourlard, and Christophe Ris.
Robust speech recognition based on multi-stream features.
In Proc. of ESCA/NATO Workshop on Robust Speech Recognition for
Unknown Communication Channels, pages 95-98, Pont-â-Mousson, France, April
1997.
[ bib |
www ]
[6]
Jean-Marc Boite, Francois Bataille, Olivier Deroo, Stephane Dupont, Vincent
Fontaine, Christophe Ris, and Laurent Zanoni.
Strut : Un logiciel complet pour l'entraînenment et la
reconnaissance de la parole.
In Proc. Premieres Journees Scientifiques et Techniques
FRANCIL, pages 41-44, Avignon, April 1997.
[ bib |
www ]
[7]
Stéphane Dupont, Hervé Bourlard, Olivier Deroo, Vincent Fontaine, and
Jean-Marc Boite.
Hybrid HMM/ANN systems for training independent tasks: Experiments
on phonebook and related improvements.
In Proc. IEEE Internat. Conf. Acoust. Speech and Signal
Process., pages 1767-1770, Munich, April 1997.
[ bib |
www ]
[8]
Hervé Bourlard and Stéphane Dupont.
Sub-band-based speech recognition.
In Proc. IEEE Internat. Conf. Acoust. Speech and Signal
Process., pages 1251-1254, Munich, April 1997.
[ bib |
www ]
[9]
Stéphane Dupont, Christophe Ris, Olivier Deroo, Vincent Fontaine, Jean-Marc
Boite, and Laurent Zanoni.
Context independent and context dependent hybrid HMM/ANN systems
for training independent tasks.
In Proc. of EUROSPEECH'97., volume 4, pages 1947-1950, Rhodes,
Greece, September 1997.
[ bib |
www ]
[10]
Stéphane Dupont and Hervé Bourlard.
Using multiple time scales in a multi-stream speech recognition
system.
In Proc. of EUROSPEECH'97., volume 1, pages 3-6, Rhodes,
Greece, September 1997.
[ bib |
www ]
[11]
Olivier Deroo, Christophe Ris, Henri Leich, Stéphane Dupont, Vincent Fontaine,
and Jean-Marc Boite.
Hybrid HMM/ANN systems for speaker independent continuous speech
recognition in french.
In Proc. of ProRISC/IEEE Workshop on Circuits, Systems and
Signal Proc., pages 137-141, Mierlo, The Netherlands, November 1997.
[ bib |
www ]
[12]
Juergen Luettin and Stéphane Dupont.
Computer Vision, volume 1407 of Lecture Notes in Computer
Science, chapter Continuous audio-visual speech recognition, pages 657-673.
Springer Berlin / Heidelberg, May 1998.
ISBN: 3-540-64613-2.
[ bib |
www ]
[13]
Stéphane Dupont.
Reconstruction de données manquantes pour la reconnaissance robuste
de la parole dans le cadre des systèmes hybrides HMM/ANN.
In Proc. XXIIèmes Journées d'Etude sur la Parole, Martigny,
Switzerland, June 1998.
[ bib |
www ]
[14]
Stéphane Dupont.
Missing data reconstruction for robust automatic speech recognition
in the framework of hybrid HMM/ANN systems.
In Proc. of Intl. Conf. on Spoken Language Processing, Sydney,
Australia, December 1998.
[ bib |
www ]
[15]
Stéphane Dupont and Juergen Luettin.
Using the multi-stream approach for continuous audio-visual speech
recognition: Experiments on the m2vts database.
In Proc. of Intl. Conf. on Spoken Language Processing, Sydney,
Australia, December 1998.
[ bib |
www ]
[16]
Stéphane Dupont and Christophe Ris.
Assessing local noise level estimation methods.
In Workshop on Robust Methods For Speech Recognition in Adverse
Conditions (Nokia, COST249, IEEE), pages 115-118, Tampere, Finland, May
1999.
[ bib |
www ]
[17]
Olivier Deroo, Christophe Ris, and Stéphane Dupont.
Context dependent hybrid HMM/ANN systems for large vocabulary
continuous speech recognition system.
In EUROSPEECH'99, Budapest, Hungary, September 1999.
[ bib ]
[18]
Stéphane Dupont.
Méthode de traitement automatique de la parole.
Patent PCT/BE01/00072, 2000.
[ bib ]
[19]
Stéphane Dupont and Juergen Luettin.
Audio-visual speech modeling for continuous speech recognition.
IEEE Transactions on Multimedia, 2000.
[ bib |
www ]
[20]
Christophe Ris and Stéphane Dupont.
Assessing local noise level estimation methods.
Speech Communication, 2000.
[ bib |
www ]
[21]
Stéphane Dupont and Leila Cheboub.
Fast speaker adaptation of hmm/ann automatic speech recognition
systems.
In Proceeding of the SPS'2000 Signal Processing Symposium,
Hilvarenbeek, The Netherlands, March 2000.
[ bib |
www ]
[22]
Stéphane Dupont.
Etude et développement d'architectures multi-bandes et
multi-modales pour la reconnaissance robuste de la parole.
PhD thesis, Faculté Polytechnique de Mons, June 2000.
[ bib |
.ps.gz ]
[23]
Stéphane Dupont and Leila Cheboub.
Fast speaker adaptation of artificial neural networks for automatic
speech recognition.
In Proceeding of ICASSP'2000, Istanbul, Turkey, June 2000.
[ bib |
www ]
[24]
Laurent Couvreur, Jean-Marc Boite, Stéphane Dupont, Christophe Ris, and
Christophe Couvreur.
Fast adaptation for robust speech recognition in reverberant
environments.
In Proc. of International Workshop on Adaptation Methods for
Speech Recognition (ITRW-2001), Sophia-Antipolis, France, August 2001.
[ bib |
.pdf ]
[25]
Carmen Benitez, Lukas Burget, Barry Chen, Stéphane Dupont, Hari Garudadri,
Hynek Hermansky, Partibha Jain, Sachin Kajarekar, and Sunil Sivadas.
Robust ASR front-end using spectral-based and discriminant
features: experiments on the aurora tasks.
In Proc. of EUROSPEECH'2001., September 2001.
[ bib |
.pdf ]
[26]
Stéphane Dupont and Christophe Ris.
Multi-band with contaminated training data.
In Proc. of CRAC workshop on consistent and reliable acoustic
cues for sound analysis., Aalborg, Denmark, September 2001.
[ bib |
.pdf ]
[27]
J. Segura, M. Benitez, A. de la Torre, S. Dupont, and A. Rubio.
Vts residual noise compensation.
In Proc. of ICASSP 2002, Orlando, Florida, May 2002.
[ bib |
.pdf ]
[28]
Andre Adami, Lukas Burget, Stéphane Dupont, Hari Garudadri, Frantisek Grezl,
Hynek Hermansky, Pratibha Jain, Sachin Kajarekar, Nelson Morgan, and Sunil
Sivadas.
Qualcomm-icsi-ogi features for asr.
In Proc. of ICSLP 2002, Denver, Colorado, September 2002.
[ bib |
.pdf ]
[29]
Harinath Garudadri, Hynek Hermansky, Lukas Burget, Pratibha Jain, Sachin
Kajarekar, Sunil Sivadas, Stéphane Dupont, Maria Carmen Benitez, and Nelson
Morgan.
System and method for computing and transmitting parameters in a
distributed voice recognition system.
Patent WO02061727/US2003004720, January 2003.
[ bib ]
[30]
Stéphane Dupont.
Subband speech processing with neural networks.
Patent EP1152399, 2003.
[ bib ]
[31]
Stéphane Dupont.
Robust parameters for noisy speech recognition.
Patent WO0184537/US2003182114, 2003.
[ bib ]
[32]
Stéphane Dupont and Christophe Ris.
Robust feature extraction and acoustic modeling at multitel:
Experiments on the aurora databases.
In Proc. of Interspeech 2003, Genève, Switzerland, September
2003.
[ bib |
.pdf ]
[33]
Harinath Garudadri, Sunil Sivadas, Hynek Hermansky, Nelson Morgan, Charles
Wooters, Andre Adami, Maria Carmen Benitez, Lukas Burget, Stéphane Dupont,
Frantisek Grezl, Pratibha Jain, Sachin Kajarekar, and Petr Motlicek.
Distributed voice recognition system utilizing multistream network
feature processing.
Patent WO03094152/US2003204394, October 2003.
[ bib ]
[34]
Stéphane Dupont and Christophe Ris.
Combined use of close-talk and throat microphones for improved speech
recognition under non-stationary background noise.
In Proc. of Robust 2004 (Workshop (ITRW) on Robustness Issues in
Conversational Interaction), Norwich, UK, August 2004.
[ bib |
.pdf ]
[35]
Stéphane Dupont and Pascale Woodruff.
Bimodal combination of speech and handwriting for improved word
recognition.
In Proc. of EUSIPCO 2005, Antalya, Turkey, September 2005.
[ bib |
.pdf ]
[36]
Stéphane Dupont, Christophe Ris, Laurent Couvreur, and Jean-Marc Boite.
A study of implicit anf explicit modeling of coarticulation and
pronunciation variation.
In Proc. of Interspeech 2005, Lisbon, Portugal, September 2005.
[ bib |
.pdf ]
[37]
Laurent Couvreur, Jean-Marc Boite, Stéphane Dupont, and Christophe Ris.
Confidence measure normalization for robust selection of asr agents.
In Proc. of SPECOM 2005, Patras, Greece, October 2005.
[ bib |
.pdf ]
[38]
Stéphane Dupont, Christophe Ris, Olivier Deroo, and Sébastien Poitoux.
Feature extraction and acoustic modeling: an approach fo improved
generalization across languages and accents.
In Proc. of ASRU 2005, San Juan, Puerto Rico, November 2005.
[ bib |
.pdf ]
[39]
Stéphane Dupont and Christophe Ris.
Multiple acoustic and variability estimation models for ASR.
In Proc. of SRIV 2006 Intarnational Workshop on Speech
Recognition and Intrinsic Variation, Toulouse, France, May 2006.
[ bib |
.pdf ]
[40]
Mohamed Benzeguiba, Renato De Mori, Olivier Deroo, Stéphane Dupont, Teodora
Erbes, Denis Jouvet, Luciano Fissore, Pietro Laface, Alfred Mertins,
Christophe Ris, Richard Rose, Vivek Tyagi, and Christian Wellekens.
Automatic speech recognition and intrinsic speech variation.
In Proc. of ICASSP 2006, Toulouse, France, May 2006.
[ bib |
.pdf ]