Original PDF Flash format stÉphane-dupont  


StÉphane Dupont

STÉPHANE DUPONT



FacultĂŠ Polytechnique de Mons, TCTS
Belgian.
31 Boulevard Dolez
Date of birth : september 3rd, 1972,
B-7000 Mons
Binche (Belgium).
Belgium
Tel. office
: + 32-65-374739
Fax office
: + 32-65-374729
E-mail : stephane.dupont@fpms.ac.be
Web
: http://tcts.fpms.ac.be/~dupont

POSITIONS HELD

MAY 2008 –
PRESENT FacultĂŠ Polytechnique de Mons (FPMS), Mons, Belgium.
Senior Researcher. Numediart research programme.
MARCH 2002 – APRIL
2008 Multitel, Mons, Belgium.
Group leader of the automatic speech recognition activities at Multitel. This non-profit
research organization is also active in the fields of speech synthesis, generic mono and
multi-dimensional signal processing, network technologies and fiber optic technologies.
OCT. 2000 – FEBR.
2002 International Computer Science Instit. (ICSI), Berkeley, California, USA.
Joint work with Qualcomm, California, USA
Post-doctoral associate. Research/development in the field of distributed speech
recognition in noisy environments. Participation to the ETSI Aurora standardization
effort (with Prof. Nelson Morgan & Hynek Hermansky).
SEPT. 1995 - SEPT.
2000 FacultĂŠ Polytechnique de Mons (FPMS), Mons, Belgium.
Researcher with a FRIA grant from the FNRS, the Belgian National Science Agency
(august 1995 - june 1999) and research assistant on the Multitel project (july 1999 -
september 2000). Research in the field of speech recognition in noisy environments and
audiovisual speech recognition (with Prof. Henri Leich and Prof. HervĂŠ Bourlard).
APRIL 1997 – JUNE
1997 Inst. Dalle Molle d'Intelligence Artif. Percept. (IDIAP), Martigny, Switzerland.
Intern. Research on audiovisual speech recognition (with Prof. HervĂŠ Bourlard).

DEGREES

JULY 2000
Ph.D., FPMS
Dissertation: “Study and development of multi-band and multi-modal architectures for
robust speech recognition’ , TCTS Dept.
JUNE 1995
Electrical Engineering Master Degree, FPMS
Dissertation: “Study and development of a pitch-to-MIDI converter’ , TCTS Dept.

SELECTED ACCOMPLISHMENTS

• More than 40 scientific publications; 168 non-self citations (according to citeseer, jun 2007).
• Awarded for best paper published in the Speech Communication journal during 2006-2008, for
paper “Automatic Speech Recognition and Speech Variability: a Review”.
• Independent expert for the European Commission Institute for Prospective Technological
Studies (JRC IPTS): validation of study on The Prospective of Speech-based Interfaces for future
Digital Services (mar 2008).
• Guest-editor of special issue “Intrinsic Speech Variation and Speech Recognition” of the Speech
Communication journal, 2006.
• Chairman and co-organizer of the “International Tutorial and Research Workshop on Speech
Recognition and Intrinsic Variation (SRIV 2006)”, Toulouse, France, May 2006 (40 participants).
• Chairman of special session “Dealing with Intrinsic Variation in ASR” at the International
Conference on Acoustic, Speech and Signal Processing, Toulouse, France, May 2006.

• Member of the Ph.D. thesis committee of Ronaldo Messina, “Acoustical Modeling for Speech
Recognition: Long Units and Multi-Modeling”, University of Avignon, France, Dec 2005.
• Best system on the ETSI Aurora3 tasks (in-car noisy speech recognition) at the Eurospeech
Conference in Genava, 2003.
• Major contributor at ICSI to the “ETSI Aurora’ competition, concerned with defining a
standard front-end algorithm for distributed speech recognition. In February 2002, our proposal
met all the requirements defined for this competition. Collaboration between ICSI, OGI
(Portland, Oregon) and Qualcomm (San Diego, California).
• Research work in the field of speech recognition under noisy conditions. This lead to a Ph.D.
dissertation and a patent application.
• Presentation of several scientific communications at diverse international conferences in the field
of signal and speech processing.
• Reviewer on a regular basis for several international scientific publications in the field of signal,
speech and image processing: EURASIP/ISCA Speech Communication Journal, EURASIP
Journal on Applied Signal Processing, IEEE Signal Processing Letters, IEEE Transactions on
Speech and Audio Processing.
• Reviewer for quality assurance plan of the FP6 HUMABIO project (2006, 2007).

MAJOR R&D GRANTS FUNDED + PROJECT PARTICIPATION

• 2007-2012: NUMEDIART (RW): project participant.
• 2006-2008: CARETAKER (EC FP6, IST): projet participant (project budget : 4.5 MgEuros)
• 2004-2007: DIVINES (EC FP6, IST): coordination of proposal writing and project
management (project budget: 3.6 MgEuros).
• 2004-2007: ALLADIN (EC FP6, IST): workpackage writing (project budget: 4.0 MgEuros).
• 2004-2007: EURAKA MAJORCALL (Eureka framework): workpackage writing and
workpackage management (partner budget 0.4 MgEuros).
• 2000-2002: DGTRE ARTHUR (Walloon Regional governement, Belgium): workpackage
writing.

INTERESTS


• RESEARCH: Speech/Language technologies, their current limitations and opportunities,
both on theoretical and practical sides, (statistical) pattern classification, detection, digital
signal processing, machine learning, multimodal interaction technologies and sensors,
computer music, artificial intelligence.
• SOFTWARE DEVELOPMENT: C, C++, scripting languages, CVS/SVN, Windows, Linux
network and cluster administration.
• RESEARCH MANAGEMENT: experience in building international research projects, in
research team management, and in intellectual property rights management.

LANGUAGES


French (fluent), English (fluent), Italian (basic skills).

UNDERGRAD STUDENTS ADVISOR
2007
• C. Versieux, “Development of standardised plug-ins for audio enhancement
and speech transformation”
• C. Huet, “Development of a bimodal speech detection system based on audio
and lip movement”

2004
• Damien Bachelart, "Multiple sensors speech recognition: combined use of
throat and close-talk microphones for improved speech detection and
recognition under noisy environments" → results have been published at an
international workshop.
• Pascale Woodruff, "Gesture-speech multimodal interface: design and
implementation of a prototype that synergistically uses automatic speech and
handwriting recognition" → results have been published at an international
conference.
• Laurent Remmerie, "Speech enhancement for post-production applications:

design and development of a text-directed model-based speech enhancement
method".

2003
• Irving Méreau, "Design and implementation of an indexing/search algorithm
for text and speech retrieval of spoken language messages".

SELECTED PUBLICATIONS
PH.D.
DISSERTATION 1. S. Dupont, Etude et dĂŠveloppement d'architectures multi-bandes et multimodales
pour la reconnaissance robuste de la parole. PhD thesis, FacultĂŠ Polytechnique de
Mons, June 2000.
INTERNATIONAL
PATENTS 2. S. Dupont, "Robust parameters for noisy speech recognition." Patent
WO/2001/084537, Intl. Application PCT/BE2001/000072, Nov. 2001.
3. H. Garudadri, H. Hermansky, L. Burget, P. Jain, S. Kajarekar, S. Sivadas, S.
Dupont, M. Ortuzar, and N. Morgan, "System and method for computing and
transmitting parameters in a distributed voice recognition system." Patent
WO/2002/061727, Intl. Application PCT/US2002/002625, Aug. 2002.
4. H. Garudadri, S. Sivadas, H. Hermansky, N. Morgan, C. Wooters, A. G. Adami, M.
C. Benitez Ortuzar, L. Burget, S. Dupont, F. Grezl, P. Jain, S. Kajarekar, and P.
Motlicek, "Ditributed voice recognition system utilizing multistream feature
processing." Patent WO/2003/094152, Intl. Application PCT/US2003/013389,
Nov. 2003.
BOOK CHAPTERS
5. Juergen Luettin and StĂŠphane 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.
PUBLISHED
REPORTS 6. Laurent Couvreur et al. “Audio Thumbnailing”. In: QPSR of the numediart
research program. Ed. by Thierry Dutoit and BenoĂŽt Macq. Vol. 1. 2. numediart.
2008. URL: http://www.numediart.org/files/numediart_2008_s2_p06_report.pdf.
Pp.: 67–85.
JOURNAL PAPERS
7. H. Bourlard, S. Dupont, and C. Ris, "Multi-stream speech recognition," (invited
paper) CC AI The Journal for the Integrated Study of Artificial Intelligence,
Cognitive Science and Applied Epistemiology, vol. 15, no. 3, pp. 215-234, 1998.
8. S. Dupont and J. Luettin, "Audio-visual speech modeling for continuous speech
recognition," IEEE Transactions on Multimedia, vol. 2, pp. 141-151, Sept. 2000.
9. C. Ris and S. Dupont, "Assessing local noise level estimation methods,"Speech
Communication, vol. 34, pp. 141-158, Apr. 2001.
10. R. De Mori, O. Deroo, S. Dupont, D. Jouvet, L. Fissore, P. Laface, A. Mertins and
C.J. Wellekens, Guest Editors, "Introduction to the Special Issue on Intrinsic
Speech Variations," Speech Communication (special issue on Intrinsic Speech
Variations), vol. 49, no. 10-11, pp. 761-762, 2007.
11. M. Benzeghiba, R. D. Mori, O. Deroo, S. Dupont, T. Erbes, D. Jouvet, L. Fissore,
P. Laface, A. Mertins, C. Ris, R. Rose, V. Tyagi, and C. Wellekens, "Automatic
speech recognition and speech variability: a review," Speech Communication
(special issue on Intrinsic Speech Variations), vol. 49, no. 10-11, pp. 763-786, 2007.
CONFERENCE
PAPERS 12. H. Bourlard, S. Dupont, H. Hermansky, and N. Morgan, "Towards subband-based
speech recognition," in Proc. of European Signal Processing Conference
(EUSIPCO), (Trieste, Italy), pp. 1579-1582, Sept. 1996.
13. 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 (ICSLP), (Philadelphia), pp. 422- 425, Oct. 1996.
14. S. Dupont and H. Bourlard, "Multiband approach for speech recognition," in Proc.
of ProRISC/IEEE Workshop on Circuits, Systems and Signal Processing, (Mierlo,
The Netherlands), pp. 113-118, Nov. 1996.
15. H. Bourlard and S. Dupont, "Sub-band-based speech recognition," in Proc. of
IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), (Munich),

pp. 1251-1254, Apr. 1997.
16. S. Dupont, H. Bourlard, O. Deroo, V. Fontaine, and J.-M. Boite, "Hybrid
HMM/ANN systems for training independent tasks: Experiments on phonebook
and related improvements," in Proc. of IEEE Intl. Conf. on Acoustics, Speech and
Signal Processing (ICASSP), (Munich), pp. 1767- 1770, Apr. 1997.
17. J.-M. Boite, F. Bataille, O. Deroo, S. Dupont, V. Fontaine, C. Ris, and L. Zanoni,
"STRUT : Un logiciel complet pour l'entra^inenment et la reconnaissance de la
parole," in Proc. of Premieres Journees Scientifiques et Techniques FRANCIL,
(Avignon), pp. 41-44, Apr. 1997.
18. S. Dupont, H. Bourlard, and C. Ris, "Robust speech recognition based on multi-
stream features," in Proc. of ESCA/NATO Workshop on Robust Speech
Recognition for Unknown Communication Channels, (Pont-Ă -Mousson, France),
pp. 95-98, Apr. 1997.
19. S. Dupont and H. Bourlard, "Using multiple time scales in a multi-stream speech
recognition system," in Proc. of European Conf. on Speech Communication and
Technology (EUROSPEECH), vol. 1, (Rhodes, Greece), pp. 3-6, Sept. 1997.
20. S. Dupont, C. Ris, O. Deroo, V. Fontaine, J.-M. Boite, and L. Zanoni, "Context
independent and context dependent hybrid HMM/ANN systems for training
independent tasks," in Proc. of European Conf. on Speech Communication and
Technology (EUROSPEECH), vol. 4, (Rhodes, Greece), pp. 1947-1950, Sept.
1997.
21. O. Deroo, C. Ris, H. Leich, S. Dupont, V. Fontaine, and J.-M. Boite, "Hybrid
HMM/ANN systems for speaker independent continuous speech recognition in
french," in Proc. of ProRISC/IEEE Workshop on Circuits, Systems and Signal
Processing, (Mierlo, The Netherlands), pp. 137-141, Nov. 1997.
22. S. Dupont and J. Luettin, "Continuous audio-visual speech recognition," in Proc. of
European Conf. on Computer Vision, (Freiburg, Germany), June 1998.
23. S. Dupont, "Reconstruction de donnĂŠes manquantes pour la reconnaissance
robuste de la parole dans le cadre des syst`emes hybrides HMM/ANN," in Proc. of
XXIIèmes Journ'ees d'Etude sur la Parole, (Martigny, Switzerland), pp. 405-408,
June 1998.
24. S. Dupont and J. 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 (ICSLP), paper 0582, (Sydney, Australia),
Dec. 1998.
25. S. 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 (ICSLP), paper 0581, (Sydney, Australia), Dec. 1998.
26. S. Dupont and C. Ris, "Assessing local noise level estimation methods," in Proc. of
Workshop on Robust Methods For Speech Recognition in Adverse Conditions
(Nokia, COST249, IEEE), (Tampere, Finland), pp. 115-118, May 1999.
27. O. Deroo, C. Ris, and S. Dupont, "Context dependent hybrid HMM/ANN systems
for large vocabulary continuous speech recognition system," in Proc. of European
Conf. on Speech Communication and Technology (EUROSPEECH), vol. 3,
(Budapest, Hungary), pp. 1095-1098, Sept. 1999.
28. S. Dupont and L. Cheboub, "Fast speaker adaptation of HMM/ANN automatic
speech recognition systems," in Proc. of SPS'2000 Signal Processing Symposium,
(Hilvarenbeek, The Netherlands), Mar. 2000.
29. S. Dupont and L. Cheboub, "Fast speaker adaptation of artificial neural networks
for automatic speech recognition," in Proc. of IEEE Intl. Conf. on Acoustics,
Speech and Signal Processing (ICASSP), vol. 3, (Istanbul, Turkey), pp. 1795-1798,
June 2000.
30. L. Couvreur, J.-M. Boite, S. Dupont, C. Ris, and C. Couvreur, "Fast adaptation for
robust speech recognition in reverberant environments," in Proc. of Intl. Workshop
(ISCA ITRW) on Adaptation Methods for Speech Recognition, (Sophia-Antipolis,
France), Aug. 2001.
31. S. Dupont and C. Ris, "Multi-band with contaminated training data," in Proc. of
CRAC workshop on consistent and reliable acoustic cues for sound analysis.,
(Aalborg, Denmark), Sept. 2001.
32. C. Benitez, L. Burget, B. Chen, S. Dupont, H. Garudadri, H. Hermansky, P. Jain, S.

Kajarekar, and S. Sivadas, "Robust ASR front-end using spectral-based and
discriminant features: experiments on the aurora tasks," in Proc. of European Conf.
on Speech Communication and Technology (EUROSPEECH), (Aalborg,
Denmark), pp. 429-432, Sept. 2001.
33. J. Segura, M. Benitez, A. de la Torre, S. Dupont, and A. Rubio, "VTS residual noise
compensation," in Proc. of IEEE Intl. Conf. on Acoustics, Speech and Signal
Processing (ICASSP), vol. 1, (Orlando, Florida), pp. 409-412, May 2002.
34. A. Adami, L. Burget, S. Dupont, H. Garudadri, F. Grezl, H. Hermansky, P. Jain, S.
Kajarekar, N. Morgan, and S. Sivadas, "Qualcomm-ICSI-OGI features for ASR," in
Proc. of Intl. Conf. on Spoken Language Processing (ICSLP), (Denver, Colorado),
pp. 21-24, Sept. 2002.
35. S. Dupont and C. Ris, "Robust feature extraction and acoustic modeling at multitel:
Experiments on the aurora databases," in Proc. of European Conf. on Speech
Communication and Technology (EUROSPEECH), (Gen`eve, Switzerland), pp.
1789-1792, Sept. 2003.
36. S. Dupont, C. Ris, and D. Bachelart, "Combined use of close-talk and throat
microphones for improved speech recognition under non-stationary background
noise," in Proc. of Intl. Workshop (ISCA ITRW) on Robustness Issues in
Conversational Interaction, (Norwich, UK), Aug. 2004.
37. S. Dupont, C. Ris, L. Couvreur, and J.-M. Boite, "A study of implicit anf explicit
modeling of coarticulation and pronunciation variation," in Proc. of
INTERSPEECH, (Lisbon, Portugal), pp. 1353-1356, Sept. 2005.
38. S. Dupont and P. Woodruff, "Bimodal combination of speech and handwriting for
improved word recognition," in Proc. of European Signal Processing Conference
(EUSIPCO), (Antalya, Turkey), Sept. 2005.
39. L. Couvreur, J.-M. Boite, S. Dupont, and C. Ris, "Confidence measure
normalization for robust selection of ASR agents," in Proc. of Intl. Conf. on
Speech and Computer (SPECOM), vol. 1, (Patras, Greece), pp. 369-372, Oct. 2005.
40. S. Dupont, C. Ris, O. Deroo, and S. Poitoux, "Feature extraction and acoustic
modeling: an approach fo improved generalization across languages and accents," in
Proc. of IEEE Automatic Speech Recognition and Understanding Workshop
(ASRU), (San Juan, Puerto Rico), pp. 29-34, Nov. 2005.
41. M. Benzeghiba, R. D. Mori, O. Deroo, S. Dupont, T. Erbes, D. Jouvet, L. Fissore,
P. Laface, A. Mertins, C. Ris, R. Rose, V. Tyagi, and C. Wellekens, "Automatic
speech recognition and intrinsic speech variation," in Proc. of IEEE Intl. Conf. on
Acoustics, Speech and Signal Processing (ICASSP), vol. 5, (Toulouse, France), pp.
1021-1024, May 2006.
42. S. Dupont and C. Ris, "Multiple acoustic and variability estimation models for
ASR," in Proc. of Intl. Workshop (ISCA ITRW) on Speech Recognition and
Intrinsic Variation (SRIV-2006), (Toulouse, France), May 2006.
43. J. Urbain, S. Dupont, T. Dutoit, R. Niewiadomski and C. Pelachaud, "Towards a
virtual agent using similarity-based laughter production", in Proc. of
Interdisciplinary Workshop on Laughter and other Interactional Vocalisations in
Speech, Berlin, February 27-28, 2009.
44. S. Dupont, T. Dubuisson, J. Urbain, R. Sebbe, N. d’Alessandro & C. Frisson,
“AudioCycle : Browsing Musical Loop Libraries”, to be published in Proc. of IEEE
Content Based Multimedia Indexing Conference (CBMI09), Chania, Greece, June
2009.
45. J. Urbain, T. Dubuisson, S. Dupont, C. Frisson, R. Sebbe & N. d’Alessandro,
“Audiocycle: a Similarity-based Visualization of Musical Libraries”, to be published
in Proc. of International Conference on Multimedia and Expo (ICME09), Cancun,
Mexico, June 2009.