Extended Summary of Laurent BESACIER

 

Bio

 

I am 34 years old. I defended my PhD thesis in Computer Science in April 1998 on “A parallel model for automatic speaker recognition” [1] at the University of Avignon (France). Then I spent one and a half year at IMT (Switzerland) as an associate researcher working on M2VTS European project (Multimodal Person Authentication). Since September 1999 I am an associate professor in Computer Science at the University Joseph Fourier (Grenoble, France). From September 2005 to October 2006, I was invited scientist at IBM Watson Research Center working on Speech to Speech Translation. My research interests can be divided in two main parts:

-1-speech and audio processing in a multimodal framework,

-2-multilingual speech recognition and (recently) translation.

 

Concerning the first part, my main contributions have been made in the domain of speech biometrics [4,5,60,65], speaker diarization [9,28,29,38] and non linguistic audio information extraction [8,21]. I recently investigated these issues in a multimodal framework: multimodal biometrics [22], information retrieval using multimodal features [26, 43, and 45] and multimodal speech analysis (cued speech) [15, 18].

 

Concerning the second part, my main contributions have been in automatic speech recognition for under-resourced languages, like Vietnamese [17, 20, and 35], Khmer [13, 16] and dialectal Arabic [14]. During my visiting year spent at IBM, I addressed the problem of law-resourced languages for automatic speech recognition and translation, especially the lack of text data. I particularly focused on the use of data-driven or fully unsupervised word decomposition algorithms for subword modeling and applied them to the following tasks and experiments:

-Data-driven morphological analysis for Iraqi ASR [14]

-Use of Multi-phone units for Iraqi-to-English speech translation [11] (a 'phone-based' speech translation approach, theoretically applicable to non written languages, was proposed)

-Fully un-supervised word decomposition for Farsi-to-English machine translation.

 

I have published papers in the best journals (Speech Communication [4], Computer Speech and Language [9]) and conferences (ICASSP [16,17,18,20,28,29,38,56,65], Interspeech [13,14,15,22,35,36,46,52,60]) of the domain and supervised or co-supervised 6 PhD students and 6 Master students.

 

Finally, I have been involved in several national and international projects : among others, I can quote NESPOLE [46,48,49,51] European project on speech-to-speech translation, M2VTS [60] European project on multimodal biometrics, as well as evaluation campaigns organized by NIST or DARPA : RT03[29], RT04[25,27], RT05[24], TRECvid[26,43,45], TRANSTAC[12].

 

Below are detailed information about my resume and a complete list of publications is available at the end of this document.

 

 

PhD and Master Students Supervision

 

 

PhD

 

Co-supervision

 

-C. Nguyen[1] (30%): Automatic Speech Recognition in Vietnamese. PhD INPG Grenoble, defended in June 2002.

-D. Vaufreydaz[2] (50%) : Using the Web for Statistical Language Modeling for ASR. PhD University J. Fourier,  Grenoble, defended in January 2002.

-D. Istrate[3] (50%) : Sound detection and recognition for medical telemonitoring. PhD INPG Grenoble, defended in December 2003.

-V-B Le[4] (70%) : ASR for under-resourced languages. PhD University J. Fourier,  Grenoble, defended in June 2006.

 

Full supervision

 

-D. Moraru[5] : Speaker diarization for audio and audiovisual documents. PhD INPG Grenoble, defended in December 2004.

-P. Mayorga[6] : ASR in the context of VoIP networks : diagnosis and proposals. PhD INPG Grenoble, defended in January 2005.

 

Masters (in French)

 

-C. Bergamini : Modèle acoustique dépendant du contexte pour la reconnaissance automatique de la parole. DEA Informatique Systèmes Communication. Université J. Fourier, Grenoble. Juin 2000. Mention B.

-R. Lamy : Adaptation de modèles acoustiques et traitement des vecteurs acoustiques pour la reconnaissance automatique de la parole téléphonique. DEA Informatique Systèmes Communication. Université J. Fourier, Grenoble. Juin 2001. Mention B.

-D. Moraru : Segmentation de signaux en locuteurs. DEA Signal Image Parole Telecom. INPG, Grenoble. Juin 2001. Mention B.

-V-B. Le : Reconnaissance automatique de mots clés en anglais en conditions bruitées. DEA Informatique Systèmes Communication. Université J. Fourier, Grenoble. Juin 2002. Mention AB.

-Q. Vu-Minh : Meilleur Interfaçage Reconnaissance / Analyse  pour la Traduction de Parole. DEA Informatique Systèmes Communication. Université J. Fourier, Grenoble. Juin 2003. Mention AB.

-B. Senechal : Etude de signatures audio-vidéo pour la recherche d’invariants de production. Master-R Signal Image Parole Telecom. INPG, Grenoble. Juin 2004. Mention AB.

 

 

International Collaborations

 

European Project NESPOLE & C-STAR Consortium

 

I was responsible for GEOD team of CLIPS of the NESPOLE (Negotiating Through SPOken Language in E-commerce) project. This was a European project on automatic speech to speech translation. The partners were ITC/IRST (Italy), CMU (USA), Univ. Karlsruhe (Germany), Aethra SA (Italy), CLIPS (France). I have been also involved in the CSTAR (Consortium for Speech Translation Advanced Research)  consortium from 1999 to 2003.

 

COST275 Action (Biometric Person Authentication over the Internet)

 

I was the co-leader of the workgroup “Evaluation” of the action. We notably proposed protocols and methodology for evaluating multimodal person authentication over the Internet, and made contributions on the effect of speech compression and packet loss on speaker verification performance due to voice over IP protocols [6].

 

SPLC

 

I am a member of SPLC (Special Interest Group on Speaker and Language Characterization) from ISCA (International Speech Communication Association). My main contribution to this is the regular participation to the scientific committee of the Speaker Odysee[7] conference.

 

Projects with Asian Labs in Vietnam and Cambodia

 

Since 1999, I have been involved in collaborations between my laboratory and Asian laboratories located in Hanoi (Vietnam) and Cambodia (Phnom-Penh). Practically, I have been selecting and supervising Vietnamese (and this year a Cambodian) PhD students that worked partly in Asia and partly in France. In parallel, I have been submitting and working on research projects to kick of speech activities in these countries and funding Master or PhD grants for young native researchers.

 

MASTOR team at IBM and DARPA TRANSTAC project (from October 2005 to October 2006)

 

The IBM MASTOR speech-to-speech translation system has been developed for the DARPA CAST and TRANSTAC programs whose mission is to develop technologies that enable rapid deployment of real-time speech translation of low-resource languages on portable devices.

More precisely, in TRANSTAC (Translation System for Tactical Use) program I contributed to develop technologies that enable robust spontaneous two-way tactical speech communications between American war fighters and native speakers. In this context, I investigated issues surrounding the rapid deployment of new languages, especially, low-resource languages and colloquial dialects.

 

Scientific Organizations and Reviewing Activities

 

-Elected member of AFCP (The French speaking speech communication association, a regional branch of ISCA)

-Reviewer for the following journals : Computer Speech and Language, IEEE Transactions on Speech and Audio Processing, IEEE Signal Processing Letters, IEEE  Transactions on Signal Processing, IEEE  Transactions on Multimedia, IEEE Transactions on Information Forensics and Security, Pattern Recognition Letters, Traitement du Signal, Acta Acustica

-Reviewer for the following conferences and workshops : ICSLP 2006, Eurospeech 2005, RECITAL 2005, Speaker Odyssee 2004 et 2006, Journées d’Etude sur la Parole 2002 2004 et 2006, ECCTD 2001,

-Elected member of the Associate professor recruiting committee” of University J. Fourier (Grenoble, France).

-Elected member of the Scientific committee of University J. Fourier (Grenoble, France)

Teaching Activities in Master

 

-Spoken Language Processing Module in University J. Fourier (Grenoble, France). Years 99/00, 00/01, 01/02, 02/03, 04/05

 

Complete list of publications

 

PhD thesis

[1] "Un modèle parallèle pour la reconnaissance automatique du locuteur" PhD, University of Avignon, April 1998.

 

International Journals

[2] "Time-frequency analysis of circumferential wave energy distribution for spherical shells. Application to sonar target recognition" P.Chevret, F.Magand, L. Besacier. Applied Signal Processing, Springer Verlag, (3). pp 136-142. 1996.

[3] "Subband approach for automatic-speaker recognition" L. Besacier, J.F. Bonastre. European Journal Signal Processing, n°80 (2000), Elsevier. Special Issue on Emerging Techniques for Communication Terminals. pp 1245-1259.

[4] "Localization and selection of speaker-specific information with statistical modeling" L. Besacier, J.F. Bonastre, C. Fredouille, Speech Communication, n°31 (2000), pp 89-106.

[5] "Overview of compression and packet loss effects in speech biometrics" L. Besacier, J.-F. Bonastre, P. Mayorga, C. Fredouille, S. Meignier, 2003 , IEE Proceedings Vision, Image & Signal Processing - Special issue on Biometrics on the Internet . Vol. 150, n°6, December 2003.

[6] "Voice biometrics over the Internet in the framework of COST action 275", L. Besacier, A. M. Ariyaeeinia, J. S. Mason, J.-F. Bonastre, P. Mayorga, C. Fredouille, S. Meignier, J. Siau, N. W. D. Evans, R. Auckenthaler, R. Stapert, EURASIP Journal on Signal Processing, Special issue on biometric signal processing. 4, 1 April 2004. p 466-479.

[7] "Système de télésurveillance sonore pour la détection des situations de détresse" Dan Istrate, M. Vacher, J. F. Serignat, L. Besacier, E. Castelli. ITBM-RBM (Elsevier) Revue Européenne de Technologie Biomédicale. 2006.

[8] « Information Extraction From Sound for Medical Telemonitoring » D. Istrate, D.; Castelli, E.; Vacher, M.; Besacier, L.; Serignat, J.-F.. IEEE Transactions on Information Technology in Biomedicine. Volume: 10  Issue: 2   Date: April 2006. pp 264-274.  

[9] « Step-by-step and Integrated approaches in broadcast news speaker diarization » Corinne Fredouille, Daniel Moraru; Sylvain Meignier, Jean-Francois Bonastre, Laurent Besacier. Computer Speech and Language Journal  pp303-330, vol 20, Issues 2-3. April-July 2006. (Elsevier).  


  Book chapter

[10] "Subband approach for automatic-speaker recognition : optimal division of the frequency domain" L. Besacier, J.F. Bonastre. Audio and Video Biometric Person Authentication. Bigun & al. eds. Lectures Notes in Computer Science 1206 (Springer Verlag), pp 195-202 / ISBN 3-540-62660-3.   

[11] « Speech Coding and Packet Loss Effects on Speech and Speaker Recognition » L. Besacier. In Automatic Speech Recognition on Mobile Devices and over Communication Networks.  Z.-H. Tan and B. Lindberg (Eds.). Springer-Verlag, London, 2008, ISBN: 978-1-84800-142-8.


 

International Conferences & Workshops

2008

 

-« Improving Pronunciation Modeling for Non-Native Speech Recognition » Tien-Ping Tan, Laurent Besacier, Interspeech 2008. Brisbane, Australia, September 2008.

-« Feature adaptation of hearing-impaired lip shapes: the vowel case in the Cued Speech context. » . Aboutabit, D. Beautemps, O. Mathieu, L. Besacier. Interspeech 2008. Brisbane, Australia, September 2008.

-« Word/Sub-word lattices decomposition and combination for Speech Recognition » V-B. Le, S. Seng, L. Besacier, B. Bigi. IEEE ICASSP 2008. Las Vegas, USA, 2008

-« First Broadcast News Transcription System for Khmer Language », S. Seng, S. Sam, L. Besacier, B. Bigi, E. Castelli. Proc. LREC 2008, Marrakech, 2008

-« WHICH UNITS FOR ACOUSTIC AND LANGUAGE MODELING FOR KHMER AUTOMATIC SPEECH RECOGNITION? », Sopheap Seng, Sethserey Sam, Viet-Bac Le, Brigitte Bigi, Laurent Besacier. 1st International Conference on Spoken Language Processing for Under-resourced languages (SLTU’2008). Hanoi, Vietnam, May 2008.

-« RECENT ADVANCES IN AUTOMATIC SPEECH RECOGNITION FOR VIETNAMESE », Viet-Bac Le, Laurent Besacier, Sopheap Seng, Brigitte Bigi, Thi-Ngoc-Diep Do. 1st International Conference on Spoken Language Processing for Under-resourced languages (SLTU’2008). Hanoi, Vietnam, May 2008.

2007

« The LIG Arabic / English Speech Translation System à IWSLT07 » L. Besacier, A. Mahdhaoui, V-B Le, IWSLT07. Trento. Italy. October 2007

« Automatic question detection: prosodic-lexical features and crosslingual experiments » V-M Quang, L. Besacier, E. Castelli, INTERSPEECH 2007. Antwerp. Belgium. August 2007.

« Modeling Context and Language Variation for Non-Native Speech Recognition » T-P Tan, L. Besacier, INTERSPEECH 2007. Antwerp. Belgium. August 2007.

« A HMM recognition of consonant-vowel syllables from lip contours: the Cued Speech case » N. Aboutabit, D. Beautemps, J. Clarke, L. Besacier, INTERSPEECH 2007. Antwerp. Belgium. August 2007.

« Automatic identification of vowels in the Cued Speech context » , Noureddine Aboutabit, Denis Beautemps, Laurent Besacier, Proc. AVSP (International Conference on Auditory-Visual Speech Processing), Hilvarenbeek (The Netherlands). September 2007.

« ON EFFICIENT COUPLING OF ASR AND SMT FOR SPEECH TRANSLATION» Bowen Zhou, Laurent Besacier and Yuqing Gao. Proceedings IEEE ICASSP 2007. Hawai, USA. April 2007.

« ACOUSTIC MODEL INTERPOLATION FOR NON-NATIVE SPEECH RECOGNITION» Tien-Ping Tan, Laurent Besacier. IEEE ICASSP 2007. Hawai, USA. April 2007.

 

2006

[11] « Towards speech translation of non written languages» Laurent Besacier, Bowen Zhou, Yuqing Gao. IEEE / ACL SLT 2006. Aruba, December 2006.

[12] « IBM MASTOR SYSTEM: Multilingual Automatic Speech-to-Speech Translator » Yuqing Gao, Gu Liang, Bowen Zhou, Ruhi Sarikaya, Mohamed Afify, Hong-Kwang Kuo, Wei-zhong Zhu, Yonggang Deng, Charles Prosser, Wei Zhang and Laurent Besacier, First International Workshop on Medical Speech Translation, in conjunction with NAACL/HLT 2006, New-York, USA. June 2006.

[13] « Comparison of Acoustic Modeling Techniques for Vietnamese and Khmer ASR », Viet Bac Le, Laurent Besacier, Proc ICSLP 2006, Pittsburgh, USA, September 2006.

[14] « ON THE USE OF MORPHOLOGICAL ANALYSIS FOR DIALECTAL ARABIC SPEECH RECOGNITION », Mohamed Afify, Ruhi Sarikaya, Hong-Kwang Jeff Kuo, Laurent Besacier, and Yuqing Gao, Proc ICSLP 2006, Pittsburgh, USA, September 2006.

[15] « Characterisation of cued speech vowels fron the inner lip contour », N. Aboutabit, D. Beautemps, L. Besacier,  Proc ICSLP 2006, Pittsburgh, USA, September 2006.

[16] « ASR AND TRANSLATION FOR UNDER-RESOURCED LANGUAGES » L. Besacier, V-B. Le, C. Boitet, V. Berment. Proceedings IEEE ICASSP 2006. Toulouse, France. May 2006.

[17] « ACOUSTIC-PHONETIC UNIT SIMILARITIES FOR CONTEXT DEPENDENT ACOUSTIC MODEL PORTABILITY » Viet Bac Le, Laurent Besacier, Tanja Schultz. IEEE ICASSP 2006. Toulouse, France. May 2006.

[18] « HAND AND LIP DESYNCHRONIZATION ANALYSIS IN FRENCH CUED SPEECH: AUTOMATIC TEMPORAL SEGMENTATION OF HAND FLOW » Noureddine Aboutabit, Denis Beautemps, Laurent Besacier. IEEE ICASSP 2006. Toulouse, France. May 2006.

[19] « A French Non-Native Corpus for Automatic Speech Recognition » Tien-Ping Tan, Laurent Besacier Proc LREC 2006. Genoa, Italy. May 2006.

2005

[20] "First steps in fast acoustic modeling for a new target language. Application to Vietnamese" Viet-Bac Le, Laurent Besacier. Proceedings IEEE ICASSP 2005. Philadelphia, USA. April 2005.

[21] "Audio, Video and Audio-Visual Signatures for Short Video Clip Detection: Experiments on Trecvid2003", Benjamin Senechal, Denis Pellerin, Laurent Besacier, Isabelle Simand, Stéphane Brès . Accepté à IEEE ICME (International Conference on Multimedia and Expo). Amsterdam. Holand. July 2005.

[22] « A Speaker independent “Liveness” Test for Audio-Visual Biometrics », Nicolas Eveno, Laurent Besacier. Accepté à Eurospeech 2005. Lisbonne, Portugal. Septembre 2005.

[23] « Speaker and Story Segmentation Using Audio-Video Information » D. Moraru, L. Besacier, G. Quenot, S. Ayache. Trends in Speech Technology. Proc. 3d Conference on Speech Technology and Human Computer Dialog. ISBN 973-27-1178-7. Cluj-Napoca, Roumania, May 13-14, 2005.

[24] « NIST RT05S Evaluation : Pre-Processing Techniques and Speaker Diarization on Multiple Microphone Meetings » Dan Istrate, Corinne Fredouille, Sylvain Meignier, Laurent Besacier, and Jean Francois Bonastre. Proc. RT05S Workshop. July 2005.

2004

[25] « Speaker Diarization in the ELISA Consortium over the last 4 years », D. Moraru, L. Besacier, S. Meignier, C. Fredouille, JF Bonastre, RT2004 Fall Workshop. November 2004.  

[26] « Video Story Segmentation with Multi-Modal Features: Experiments on TRECvid 2003 », L. Besacier, G. Quenot, S. Ayache, D. Moraru, 6th ACM SIGMM International Workshop on Multimedia Information Retrieval, October 15-16,  2004,  New York, NY USA.  

[27] « The NIST 2004 spring rich transcription evaluation : two-axis merging strategy in the context of multiple distance microphone based meeting speaker segmentation », C. Fredouille, D. Moraru, S. Meignier, L. Besacier, J.-F. Bonastre, RT2004 Spring Meeting Recognition Workshop, May 17, 2004.

[28] “Benefit of prior acoustic segmentation for speaker segmentation systems” S. Meignier, D. Moraru, C. Fredouille, L. Besacier, and J.-F. Bonastre, International Conference on Acoustics Speech & Signal Processing (ICASSP), Montreal, Canada, May 2004.

[29] “The ELISA consortium approaches in Broadcast News speaker segmentation during the NIST 2003 Rich Transcription evaluation”. D. Moraru, S. Meignier, C. Fredouille, L. Besacier, and J.-F. Bonastre, International Conference on Acoustics Speech & Signal Processing (ICASSP), Montreal, Canada, May 2004.

[30] “Using a priori information for speaker diarization”, Daniel Moraru, Laurent Besacier, Eric Castelli Proc. Odyssee 2004, The Speaker and Language Recognition Workshop, Toledo, Spain, 31 May-4 June, 2004.

[31] "ELISA Nist RT03 Broadcast News Speaker Diarization Experiments" Daniel Moraru, Sylvain Meignier, Corinne Fredouille, Laurent Besacier, Jean-François Bonastre, Proc. Odyssee 2004, The Speaker and Language Recognition Workshop, Toledo, Spain, 31 May-4 June, 2004.

[32] "SPOKEN AND WRITTEN LANGUAGE RESOURCES FOR VIETNAMESE" Viet-Bac Le , Do-Dat Tran, Eric Castelli, Laurent Besacier, Jean-François Serignat, Proc. LREC2004, Lisbonne, Portugal. 2004

[33] « Spoken Dialogue Translation Systems Evaluation: Results, New Trends, Problems and Proposals » Hervé Blanchon, Christian Boitet, Laurent Besacier. Proc. IWSLT 2004 (ICLSP 2004 Satellite Workshop). Kyoto, Japan. September 30 - October 1, 2004. vol. 1/1: pp. 95-102.  

 
 
 

2003

[34] "AUDIO PACKET LOSS OVER IP AND SPEECH RECOGNITION ", Pedro Mayorga, Laurent Besacier, Richard Lamy and Jean-Francois Serignat, ASRU 2003 (Automatic Speech recognition & Understanding), Virgin Islands, USA, Dec 2003.

[35] "Using the Web for fast language model construction in minority languages" Viet Bac LE, Brigitte BIGI, Laurent BESACIER, Eric CASTELLI, Eurospeech 2003, Geneva, 1-4 Sept. 2003.  

[36] "The NESPOLE! VoIP Multilingual Corpora  in Tourism and Medical Domains" Nadia Mana, Susanne Burger, Roldano Cattoni,
Laurent Besacier, Victoria MacLaren, John McDonough, Florian Metze, Eurospeech 2003, Geneva, 1-4 Sept. 2003.
 

[37] "Smart Audio Sensor for Telemedicine" Michel Vacher, Dan Istrate, Laurent Besacier, Eric Castelli, Jean-Francois Serignat, Smarts Objects Conference (SOC) 2003, 15-17 May, Grenoble, France.

[38] "The ELISA consortium approaches in speaker segmentation during the NIST 2002 speaker recognition evaluation", D. Moraru, S. Meignier, L. Besacier, J-F Bonastre, I. Magrin-Chagnolleau. Accepted to International Conference on Acoustics Speech & Signal Processing (ICASSP), Honk-Kong, China, May 2003.

[39] "Towards Conversational Model for Speaker Segmentation", D. Moraru, L. Besacier, "Speech Technology & Human-Computer Dialogue", Bucharest, April 10-11, 2003, ISBN 973-27-0963-4.<zip>

[40] "HABITAT TELEMONITORING SYSTEM BASED ON THE SOUND SURVEILLANCE" Eric Castelli, Michel Vacher, Dan Istrate, Laurent Besacier, Jean-Francois Serignat, ICICTH (International Conference on Information Communication Technologies in Health), 11-13 July 2003, Samos Island, Greece.  

[41] "Life Sounds Extraction and Classification in Noisy Environment" M. Vacher and D. Istrate and L. Besacier and J.F.Serignat and E. Castelli, IASTED International Conference on Signal & Image Processing, 12-14 August 2003, Kauai, 2003.  

[42] "Non-linear acoustical pre-processing for multiple sampling rates ASR and ASR in noisy condition", Richard LAMY, Laurent BESACIER, worshop NOLISP 03, Le Croisic, France, 20-23 mai 2003.  

[43] “CLIPS at TRECvid: Shot Boundary Detection and Feature Detection”, Georges M. Quénot, Daniel Moraru, Laurent Besacier, 12th Text Retrieval Conference, Gaithersburg, MD, USA, 2003.

 

2002

 

[44] METHODOLOGY FOR EVALUATING SPEAKER VERIFICATION ROBUSTNESS OVER IP NETWORKS L. Besacier, P. Mayorga, J.F. Bonastre, C. Fredouille, Proceedings of the COST275 Workshop on The Advent of Biometrics on the Internet, Rome, Nov 2002, ISBN 92-894-4848-2  

[45] "CLIPS-IMAG at TREC-11 : Experiments in Video Retrieval", Georges M. Quénot, Daniel Moraru, Laurent Besacier, and Philippe Mulhem  , 11th Text Retrieval Conference, Gaithersburg, MD, USA, 19-22 November, 2002.

[46] S. Rossato, H. Blanchon, L. Besacier “Speech-to-speech translation system evaluation : results for French for the Nespole! Project first showcase”, Proc ICSLP2002, Denver, USA, Sept 2002.

[47] P. Mayorga-Ortiz, R. Lamy, L. Besacier “Recovering of packet loss for distributed speech recognition”, Proc. Eusipco 2002, Toulouse, France, Sept. 2002.

[48] The Nespole Project Consortium : A. Lavie, F. Metze, R. Cattoni, E. Costantini, S. Burger, D. Gates, C. Langley, K.Laskowski, L. Levin, K. Peterson, T. Schultz, A. Waibel, D. Wallace, J. MacDonough, H. Soltau, G. Lazzari, N. Mana, F. Pianesi, E. Pianta, L. Besacier, H. Blanchon, D. Vaufreydaz “A Multi-Perspective Evaluation of the Nespole! Speech-to-Speech Translation System”, Proc. ACL2002 Workshop on Speech-to-Speech Translation : Algorithms and Systems, Philadelphia, PA, July 7-12 2002

[49] The Nespole Project Consortium  “The NESPOLE! Speech-to-Speech Translation System”, Proc HLT (Human Language Technologies) 2002, San-Diego, CA

[50] The Nespole Project Consortium “Enhancing the Usability and Performance of NESPOLE! - a Real-World Speech-to-Speech Translation System”, Proc HLT (Human Language Technologies) 2002, San-Diego, CA

 


2001

[51] D. Vaufreydaz, L. Besacier , C. Bergamini, R. Lamy, “From generic to task-oriented speech recognition: French experience in the NESPOLE! European project", presented at ITRW Workshop on Adaptation Methods for Speech Recognition, Sophia-Antipolis, France 29-30 August, 2001,   

[52] L. Besacier, H. Blanchon, Y. Fouquet, J.P. Guilbaud, S. Helme, S. Mazenot, D. Moraru, D. Vaufreydaz "Speech Translation for French in the NESPOLE! European Project", Eurospeech 2001, Aalborg, Danemark, September 2001.  

[53] S. Burger, L. Besacier, P. Coletti, F. Metze, C. Morel "The NESPOLE! VoIP Dialogue Database", Eurospeech 2001, Aalborg, Danemark, September 2001.  

[54] L. Besacier , C. Bergamini, D. Vaufreydaz, E. Castelli "THE EFFECT OF SPEECH AND AUDIO COMPRESSION ON SPEECH RECOGNITION PERFORMANCE " IEEE Multimedia Signal Processing Workshop, Cannes, France, October 2001.  


2000

[55] D. Vaufreydaz, C. Bergamini, J. F. Serignat, L. Besacier and M. Akbar, “A New Methodology for Speech Corpora Definition from Internet Documents,”  presented at LREC'2000, 2nd International Conference on Language Ressources and Evaluation, Athens, Greece, 31 May-2 June, 2000, I, pp.423-426.  

[56] "GSM Speech Coding and Speaker Recognition,”  L. Besacier, S. Grassi, A. Dufaux, M. Ansorge and F. Pellandini, presented at ICASSP 2000, Istambul, Turkey, 5-9 june, 2000 .

[57] "INFLUENCE OF GSM SPEECH CODING ON THE PERFORMANCE OF TEXT-INDEPENDENT SPEAKER RECOGNITION" S. Grassi, L. Besacier, A. Dufaux, M. Ansorge, and F. Pellandini.EUSIPCO 2000, Tampere, Finland, Sept. 4-8, 2000  

[58] "AUTOMATIC SOUND DETECTION AND RECOGNITION FOR NOISY ENVIRONMENT", Alain Dufaux, Laurent Besacier, Michael Ansorge, and Fausto Pellandini, EUSIPCO 2000, Tampere, Finland, Sept. 4-8, 2000  

[59] "SPEAKER RECOGNITION ON COMPRESSED SPEECH" S. Grassi , A. Dufaux , L. Besacier , M. Ansorge , F. Pellandini, Workshop on friendly exchanging through the net, Bordeaux (France), March 22-24, 2000.

 

1999

[60] "Experimental Evaluation of Text-independent Speaker Verification on Laboratory and Field Test Databases in the M2VTS project" L. Besacier, J. Luettin, G. Maître, E. Meurville. Eurospeech 99. Budapest, Hungary. 5-9 September 99.   

[61] "Automatic Sound Recognition relying on statistical methods, with application to telesurveillance". L. Besacier, A. Dufaux, M. Ansorge, and F. Pellandini. International Workshop on Intelligent Communication Technologies and Applications, with emphasis on mobile communications. Neuchâtel, Switzerland. May, 5-7, 1999.    

[62] "Influence of GSM speech coding algorithms on text-independent speaker identification performance". S. Grassi, L. Besacier, A. Dufaux, M. Ansorge, F. Pellandini. International Workshop on Intelligent Communication Technologies and Applications, with emphasis on mobile communications. Neuchâtel, Switzerland. May, 5-7, 1999.   

[63] "Multi Modal Verification for Teleservices and Security Applications (M2VTS)" G. Richard, Y. Menguy, I. Guis, N. Suaudeau, J. Boudy, P. Lockwood, C. Fernandez, F. Fernández, C. Kotropoulos, I. Pitas, R. Heimgartner, P. Ryser, C. Beumier, S. Pigeon, G. Matas, J. Kittler,  J. Bigün, Y. Abdeljaoued, E. Meurville, L. Besacier , G.Maitre, J. Luettin, S. Ben-Yacoub B. Ruiz. In Proc. IEEE Conference on Multimedia Computing and Systems’99. Florence, Italy, 7-11 June 1999.

[64] "Automatic Detection and Classification of Wideband Acoustic Signals" A. Dufaux, L. Besacier, M. Ansorge, F. Pellandini. Joint 137th meeting of the Acoustical Society of America and Forum Acusticum 99. Berlin, Germany. 14-19 March, 1999.

 

 

1998

[65] "Frame Pruning for Speaker Recognition". L. Besacier, J.F. Bonastre. Proc. IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 12-15 May 1998. Seattle (USA).   

[66] "Time and frequency pruning for speaker identification". L. Besacier. Proc 14th International Conference on Pattern Recognition (ICPR), 16-20 August 1998. Brisbane (Australia).   

[67] "Frame Pruning for Speaker Recognition". L. Besacier, J.F. Bonastre. Proc. Eusipco, 8-11 September 1998. Rhodes (Greece).   

[68] "Time and frequency pruning for speaker identification" L. Besacier, J.F. Bonastre. Proc. on Speaker Recognition and its Commercial and Forensic Applications (RLA2C), 20-23 April, 1998. Avignon (France).   

 

 

1997

[69] "Independent processing and recombination of partial frequency bands for automatic speaker recognition" L. Besacier, J.F. Bonastre. Fourteenth Internationnal Conference on Speech Processing. IEEE Korea Council, IEEE Korea Signal Processing Society, Seoul, Korea, August 26-28, 1997.   

[70] "Subband architecture for automatic speaker recognition on partially corrupted speech" L. Besacier, J.F. Bonastre. COST 254 Workshop on emerging techniques for communication terminals. Toulouse, France. 7-9 July 1997.   

 

1995

[71] "Time frequency analysis of Stoneley wave energy distribution for spherical and cylindrical shells. Application to sonar target recognition." P.Chevret, F.Magand, L. Besacier, . UK Symposium on applications of time-frequency and time-scale methods. pp 233-240. Coventry, UK, 30-31 Aout 1995.


National Conferences 

[72] « Reconnaissance Automatique de la Parole pour des Langues peu Dotées : Application au Vietnamien et au Khmer » L. Besacier , V.-B. Le , E. Castelli, S. Sethserey , L. Protin , TALN 2005 – Atelier TALN et langues mal dotées. Dourdan, France. Juin 2005.  

 [73] "Premiers pas du CLIPS sur les données d’évaluation ESTER", R. Lamy, D. Moraru, B. Bigi, L. Besacier, JEP 2004, Fès, Maroc, Avril 2004

 [74]  "Segmentation selon le locuteur: les activités du Consortium ELISA dans le cadre de Nist RT03", D. Moraru, S. Meignier, C. Fredouille, L. Besacier, J-F Bonastre, JEP 2004, Fès, Maroc, Avril 2004

 [75] Vu Minh, Q., Besacier, L., Castelli, E., Bigi, B., and Blanchon, H.. (2004). Interchange format-based language model for automatic speech recognintion in speech-to-speech translation. Proc. RIVF'04 (Recherche Informatique Vietnam-Francophonie). To be published in a special issue of Studia Informatica Universalis [Suger Editor]. February 2-5, 2004. vol. 1/1: pp. 47-50.

[76] Hervé Blanchon, Laurent Besacier « Traduction de dialogue: résultats du projet NESPOLE! et pistes pour le domaine » TALN 2004, Session Poster, Fès, 19-21 avril 2004.

 [77] Quang Vu-minh, Laurent Besacier, Hervé Blanchon, Brigitte Bigi  « Modèle de langage sémantique pour la reconnaissance automatique de parole dans un contexte de traduction » TALN 2004, Session Poster, Fès, 19-21 avril 2004.

[78] D. Moraru, L. Besacier « Segmentation en locuteurs de conversations sur IP », XXIVèmes Journées d’Etude sur la Parole, Nancy, Juin 2002.

[79] R. Lamy, L. Besacier “Adaptation spectrale par quantification vectorielle : exemple de la RAP à fréquences d’échantillonnage multiples”, XXIVèmes Journées d’Etude sur la Parole, Nancy, Juin 2002.

[80] S. Rossato, H. Blanchon, L. Besacier “Évaluation du premier démonstrateur de traduction de parole dans le cadre du projet NESPOLE!”, Congrès TALN (Traitement Automatique du Langage Naturel), Nancy, Juin 2002.

[81] "Système d'élagage temps-fréquence pour l'identification du locuteur" L. Besacier, J.F. Bonastre. 22èmes Journées d'Etude sur la Parole. Martigny, Suisse. 15-19 Juin 1998.   

[82] "Architecture en sous-bandes pour la reconnaissance automatique du locuteur en milieu bruite" L. Besacier, J.F. Bonastre, C. Fredouille. Proc. RFIA 98. Clermont-Ferrand, France. 20-22 Janvier 1998.

[83] " Traitement indépendant de sous-bandes fréquentielles par des méthodes statistiques du second ordre pour la reconnaissance automatique du locuteur. " L. Besacier, J.F. Bonastre. 4th French Congress on Acoustics. Marseille, France, 14-18 April 1997.

[84] "Caractéristiques individuelles de la durée vocalique intrinsèque en français lu; une étude pilote. " D. Duez, L. Besacier. 4th French Congress on Acoustics. Marseille, France, 14-18 April 1997.

 



[1] C. Nguyen is now associate professor at Polytechnic Institute of Hanoï (Viet-Nam)

[2] D. Vaufreydaz is now associate professor at University Pierre Mendes-France (Grenoble, France)

[3] D. Istrate is now associate professor at ESIGETEL (Fontainebleau, France)

[4] V-B Le has now a postdoctoral position in LORIA, (Nancy, France).

[5] D. Moraru is now a research engineer for Motorola

[6] P. Mayorga is now associate professor at  University of Mexicali (Mexico)

[7] http://www.speakerodyssey.com/