EURECOM - Communication Systems - Christian WELLEKENS

Multimedia Communications

Back

Christian WELLEKENS Professor Emeritus

Email	Christian WELLEKENS
Phone	+32 472 46 91 77
Fax

Resume

Education

Christian Wellekens received the degree of Ingénieur Civil Electricien Mécanicien from the University of Louvain, Belgium in 1965 and the Ph.D. from the Ecole Polytechnique Fédérale de Lausanne, Switzerland in 1974.

Since his retirement, he studies for a Master in Philosophy at the University of Louvain (graduation planned in 2011).

Teaching

From 1969 to 1992, he was a lecturer in electronics and circuit theory at Ecole Centrale des Arts et Métiers (ECAM), Brussels.
In September 1992, he joined EURECOM as a full Professor and headed the Multimedia Communications Department until October 1998.
He retired from EURECOM on 2007 where he is now active as Professor emeritus.

Industrial experience
He worked for MBLE Research Labs (Philips development) from 1965-68 where he developed microwave power amplifiers. In 1968, he joined the Philips Research Laboratory (PRLB) where he stayed till March 1991. He worked successively on the mathematical approximation of specifications of analog and digital filters, on piezoelectric transducer modeling and on speech recognition.
He spent a sabbatical year (1989-1990) at Bellcore (Bell Communications Research), Morristown, N.J USA. His main contributions were in circuit theory, signal processing, speech recognition, connectionist networks and applied mathematics.
From March 1991 to September 1992, he was a Scientific Advisor for Speech Recognition at Lernout & Hauspie Speech Products (Belgium) where he contributed to the development of industrial speech recognizers using stochastic models as well as neural networks.

Major research interests

Speech recognition in adverse environmemt and under major intrinsic variabilities like speech rate, speaker‘s stress, Signal processing, Stochastic models.

Visibility, membership, committee

He is a Life Senior Member of IEEE.
He was a member of the first IEEE-TC on Neural Networks.
He was a member of the IEEE STC in 2002-2005.

He was an elected member of the ISCA board from 2000 to 2007 and is still an ex-officio member as its ISCApad newsletter editor.

Additional information

Distinctions

He co-authored the paper winning the ISCA 2009 best paper award at the interspeech conference in Brighton, «Automatic speech recognition and speecb variability: a review» published in the speech communication journal. Sept. 10, 2009.
In 2005, he received the Christoffel Plantin Award (Belgium) as an outstanding Belgian personality working abroad.

Selected publications

Cernak, Milos; Wellekens, Christian J W Emotional aspects of intrinsic speech variabilities in automatic speech recognition SPECOM’2006, 11th International Conference Speech and Computer - June 25-29, 2006, Saint-Petersburg, Russia (EURECOM Ref: 1899)
BenZeghiba, Mohamed Faouzi; Wellekens, Christian J W Confidence measures for tandem connectionist feature extraction Rapport de recherche RR-06-166 (EURECOM Ref: 1967)
BenZeghiba, Mohamed Faouzi; De Mori, Renato; Deroo, Olivier; Dupont, Stéphane; Erbes, Teodora;J ouvet, Denis; Fissore, Luciano ; Laface, Pietro; Mertins, Alfred; von Ossietzky, Carl; Ris, Christophe; Rose, Richard; Tyagi,Vivek; Wellekens, Christian J W Dealing with intrinsic speech variabilities in ASR ICASSP 2006, 31st International Conference on Acoustics, Speech, and Signal Processing, May 14-19, 2006, Toulouse, France (EURECOM Ref: 1903)

Publications

Eurecom Reference	2007
2364	De Mori, R;Deroo, O;Dupont, S;Jouvet, D;Fissore, L;Laface, P;Mertins, A;Wellekens, Christian J Introduction to the special issue on intrinsic speech variations Speech Communication, Volume 49, Issues 10-11, October-November 2007 , pp 761-762 Details BibTeX DOI
2363	Benzeghiba, Mohamed;De Mori, R;Deroo, O;Erbes, T;Jouvet, D;Fissore, L; Laface, P;Mertins, A;Ris, C;Rose, R;Tyagi, Vivek;Wellekens, Christian J Automatic speech recognition and speech variability: A review Speech Communication, Volume 49, Issues 10-11, October-November 2007 , pp 763-786 Details BibTeX DOI
2157	Pettersen, Svein Gunnar;Johnsen, Magne Hallstein;Wellekens, Christian J Variational Bayesian learning of speech GMMS for feature enhancement based on Algonquin ICASSP 2007, 32nd IEEE International Conference on Acoustics, Speech, and Signal Processing, April 15 - 20, 2007, Honolulu, USA Details BibTeX DOI
2171	Cernak, Milos;Benzeghiba, Mohamed;Wellekens, Christian J Diagnostics of speech recognition : on evaluating feature set performance Rapport de recherche RR-07-190 Details BibTeX
Eurecom Reference	2006
2130	BenZeghiba, Mohamed Faouzi;Wellekens, Christian J Investigations into tandem features Rapport de recherche RR-06-185 Details BibTeX
2131	Brayda, Luca;Wellekens, Christian J;Matassoni, Marco;Omologo, Maurizio Speech recognition in reverberant environments using remote microphones ISM 2006, 8th IEEE International Symposium on Multimedia, December 11-13, 2006, San Diego, USA Details BibTeX DOI
2021	Cernak, Milos;Wellekens, Christian J Diagnostics of speech recognition using classification phoneme diagnostic trees CI 2006, 2nd IASTED International Conference on computational intelligence, Special Session on NLP, November 20-22, 2006 San Francisco, USA Details BibTeX DOI File request
2004	Tyagi, Vivek;Wellekens, Christian J;Slock, Dirk T M Least squares filtering of speech signals for robust ASR Speech Communication, Volume 48, Issue 11, November 2006 , pp 1528-1544 Details BibTeX DOI
2133	Brayda, Luca;Wellekens, Christian J;Omologo, Maurizio N-Best parallel maximum likelihood beamformers for robust speech recognition EUSIPCO 2006, European Signal Processing Conference, September 4-8, 2006, Firenze, Italy Details BibTeX
1935	Tyagi, Vivek;Bourlard, Hervé;Wellekens, Christian J On variable-scale piecewise stationary spectral analysis of speech signals for ASR Speech Communication, Volume 48, Issue 9, September 2006 , pp 1182-1191 Details BibTeX DOI
2054	Brayda, Luca;Wellekens, Christian J;Omologo, Maurizio Improving robustness of a likelihood-based beamformer in a real environment for automatic speech recognition SPECOM'2006, 11th International Conference Speech and Computer - June 25-29, 2006, Saint-Petersburg, Russia Details BibTeX
1899	Cernak, Milos;Wellekens, Christian J Emotional aspects of intrinsic speech variabilities in automatic speech recognition SPECOM'2006, 11th International Conference Speech and Computer - June 25-29, 2006, Saint-Petersburg, Russia Details BibTeX
2052	BenZeghiba, Mohamed Faouzi;De Mori, Renato;Deroo, Olivier;Dupont, Stéphane;Jouvet, Denis;Fissore, Luciano;Laface, Pietro;Mertins, Alfred;Ris, Christophe;Rose, Richard;Tyagi, Vivek;Wellekens, Christian J Impact of variabilities on speech recognition SPECOM'2006, 11th International Conference Speech and Computer - June 25-29, 2006, Saint-Petersburg, Russia Details BibTeX
2132	Brayda, Luca;Wellekens, Christian J;Omologo, Maurizio Reconnaissance robuste de parole en environnement reél à l'aide d'un réseau de microphones à formation de voie adaptative basée sur un critère des N-best vraisemblance maximale JEP 2006, Journees d'Etudes sur la Parole , 12-16 juin 2006, Dinard, France Details BibTeX DOI
1967	BenZeghiba, Mohamed Faouzi;Wellekens, Christian J Confidence measures for tandem connectionist feature extraction Rapport de recherche RR-06-166 Details BibTeX
2055	Tyagi, Vivek; BenZeghiba, Mohamed Faouzi;Cernak, Milos;Wellekens, Christian J Comparative study of different features on OLLO logatome recognition task SRIV 2006, ITRW on Speech Recognition and Intrinsic Variation, May 20, 2006, Toulouse, France Details BibTeX DOI
1936	Tyagi, Vivek;Wellekens, Christian J Fepstrum and carrier signal decomposition of speech signals through homomorphic filtering ICASSP 2006, 31st International Conference on Acoustics, Speech, and Signal Processing - Special session, Dealing with intrinsic speech variabilities in ASR, Volume 5, May 14-19, 2006, Toulouse, France Details BibTeX DOI
1903	BenZeghiba, Mohamed Faouzi;De Mori, Renato;Deroo, Olivier; Dupont, Stéphane;Erbes, Teodora;Jouvet, Denis; Fissore, Luciano;Laface, Pietro;Mertins, Alfred;Ris, Christophe;Rose, Richard; Tyagi,Vivek;Wellekens, Christian J Automatic speech recognition and intrinsic speech variation ICASSP 2006, 31st International Conference on Acoustics, Speech, and Signal Processing, May 14-19, 2006, Toulouse, France Details BibTeX DOI
Eurecom Reference	2005
1719	Tyagi, Vivek;Wellekens, Christian J Fepstrum representation of speech signal ASRU 2005, IEEE Automatic Speech Recognition and Understanding Workshop, November 27-December 1, 2005, Cancun, Mexico , pp 11-16 Details BibTeX DOI
1835	Tyagi, Vivek;Wellekens, Christian J Adaptive enhancement of speech signals for robust ASR ASIDE 2005, COST 278 Final Workshop and ISCA Tutorial and Research Workshop, 10-11 November 2005, Aalborg, Denmark Details BibTeX DOI File request
1693	Valente, Fabio;Wellekens, Christian J Regroupement de modèles de locuteurs par méthode Bayesienne variationnelle: applications à la sélection de modèles par méthode variationnelle pour l’indexation audio t.a.l.,traitement automatique des langues, Volume 45 N° 3, octobre 2005. Numero spécial des meilleurs articles JEP-TALN 2004 Details BibTeX DOI
1663	Tyagi, Vivek;Wellekens, Christian J;Bourlard, Hervé On variable-scale piecewise stationary spectral analysis of speech signals for ASR Interspeech 2005, 9th European Conference on Speech Communication and Technology, September 4-8, 2005, Lisbon, Portugal Details BibTeX DOI
1691	Valente, Fabio;Wellekens, Christian J Variational Bayesian speaker change detection Interspeech 2005, 9th European Conference on Speech Communication and Technology, September 4-8, 2005, Lisbon, Portugal Details BibTeX DOI
1661	Tyagi, Vivek;Wellekens, Christian J;Bourlard, Hervé A variable-scale piecewise stationary spectral analysis technique applied to the ASR MLMI 2005, 2nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms, July 11-13, 2005, Edinburgh, UK Details BibTeX DOI
1692	Valente, Fabio;Wellekens, Christian J Variational Bayesian methods for audio indexing MLMI 2005, 2nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms, July 11-13, 2005, Edinburgh, UK - Also published in LNCS Volume 3869, 2006 , pp 307-319 Details BibTeX DOI
1720	Tyagi, Vivek;Wellekens, Christian J Least squares filtering of speech signals for robust ASR MLMI 2005, 2nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms, 11-13 July 2005, Edinburgh, UK - Also published as LNCS 3869 Details BibTeX DOI
1568	Valente, Fabio;Wellekens, Christian J Variational bayesian feature saliency for audio type classification ICASSP 2005, 30th IEEE International Conference on Acoustics, Speech, and Signal Processing, March 18-23, 2005- Philadelphia, USA Details BibTeX DOI
1569	Valente, Fabio;Wellekens, Christian J Variational bayesian adaptation for speaker clustering ICASSP 2005, 30th IEEE International Conference on Acoustics, Speech, and Signal Processing, March 18-23, 2005- Philadelphia, USA Details BibTeX DOI
1571	Tyagi, Vivek;Wellekens, Christian J On desensitizing the Mel-cepstrum to spurious spectral components for robust speech recognition ICASSP 2005, 30th IEEE International Conference on Acoustics, Speech, and Signal Processing, March 18-23, 2005- Philadelphia, USA Details BibTeX DOI
Eurecom Reference	2004
1458	Valente, Fabio;Wellekens, Christian J Scoring unknown speaker clustering : VB vs. BIC ICSLP 2004, 8th Biennial Conference of International Conference on Spoken Language Processing, October 4-8, 2004, Jeju Island, Korea Details BibTeX DOI
1513	Tyagi, Vivek;Wellekens, Christian J On desensitizing the Mel-cepstrum to spurious spectral components for robust speech recognition Rapport de recherche RR-04-119 Details BibTeX
1514	Tyagi, Vivek;Wellekens, Christian J On multi-scale piecewise stationary spectral analysis of speech signals for robust ASR Rapport de recherche RR-04-118 Details BibTeX
1498	Tyagi, Vivek;Wellekens, Christian J On de-emphasizing the spurious components in the spectral modulation for robust speech recognition Robust 2004, COST 278 and ISCA Tutorial and Research Workshop Robustness Issues in Conversational Interaction August, 30-31, 2004, Norwich, UK Details BibTeX DOI File request
1418	Valente, Fabio;Wellekens, Christian J Variational Bayesian speaker clustering Odyssey'2004, The speaker and language recognition workshop, May 31- June 3, 2004, Toledo, Spain Details BibTeX DOI
1321	Valente, Fabio;Wellekens, Christian J Variational Bayesian feature selection for gaussian mixture models ICASSP 2004, 29th IEEE International Conference on Acoustics, Speech, and Signal Processing, May 17-21, 2004, Montreal, Canada , pp 513-16 vol.1 Details BibTeX DOI
1419	Valente, Fabio;Wellekens, Christian J Regroupement bayesien variationnel des locuteurs JEP'2004, 25èmes Journées d'étude de la parole, 19-22 avril 2004, Fès, Maroc Details BibTeX DOI
1341	Junqua, Jean-Claude;Wellekens, Christian J Editorial of Special issue on adaptation methods for speech recognition Speech Communication Volume 42, Issue 1, January 2004 , pp 1-3 Details BibTeX DOI
Eurecom Reference	2003
1261	Valente, Fabio;Wellekens, Christian J Maximum entropy discrimination (MED) feature subset selection for speech recognition ASRU 2003, IEEE Automatic Speech Recognition and Understanding Workshop, November 30 -- December 4, 2003, St. Thomas, Virgin Islands, USA Details BibTeX DOI
1260	Valente, Fabio;Wellekens, Christian J Maximum entropy discrimination (MED) feature subset selection for speech recognition Rapport de recherche RR-03-086 Details BibTeX
1259	Valente, Fabio;Wellekens, Christian J Variational Bayesian features selection Rapport de recherche RR-03-087 Details BibTeX
1194	Valente, Fabio;Wellekens, Christian J Variational bayesian GMM for speech recognition Eurospeech 2003, 8th european conference on speech communication and technology - September 1-4, 2003, Geneva, Switzerland Details BibTeX DOI
1195	Valente, Fabio;Wellekens, Christian J Variational bayesian learning for gaussian mixture models and hidden markov models Rapport de recherche RR-03-079 Details BibTeX
1209	Lee, Kyung-Tak;Melnar, Lynette;Talley, Jim;Wellekens, Christian J Symbolic speaker adaptation with phone inventory expansion ICASSP 2003, 28th IEEE International Conference on Acoustics, Speech, and Signal Processing, April 6-10, 2003 - Hong Kong Details BibTeX
1193	Valente, Fabio;Wellekens, Christian J Minimum classification error /eigenvoices training for speaker identification ICASSP 2003, 28th IEEE International Conference on Acoustics, Speech, and Signal Processing, April 6-10, 2003 - Hong Kong Details BibTeX DOI
Eurecom Reference	2002
823	Nguyen, Patrick;Rigazio, Luca;Wellekens, Christian J;Junqua, Jean-Claude Lu factorization for feature transformation ICSLP'2002, 7th International Conference on Spoken Language Processing, 16- 20 September 2002, Denver, USA , pp 73-76 Details BibTeX DOI
751	Nguyen, Patrick;Rigazio, Luca;Junqua, Jean-Claude;Wellekens, Christian J Piecewise linear constraints for model space adaptation ICASSP 2002 , 27th IEEE International Conference on Acoustics, Speech and Audio Processing - May 13-17, 2002, Orlando, USA Details BibTeX DOI
Eurecom Reference	2001
713	Nguyen, Patrick;Rigazio, Luca;Wellekens, Christian J;Junqua, Jean-Claude Construction of model-space constraints ASRU 2001, IEEE Workshop on Automatic Speech Recognition and Understanding, December 9-13 2001, Madonna di Campiglio, Trento, Italy Details BibTeX
738	Lee, Kyung-Tak;Wellekens, Christian J Dynamic sharings of gaussian densities using phonetic features ASRU 2001, IEEE Workshop on Automatic Speech Recognition and Understanding, December 9-13 2001, Madonna di Campiglio, Trento, Italy Details BibTeX
739	Lee, Kyung-Tak;Wellekens, Christian J Dynamic lexicon using phonetic features Eurospeech 2001, 7th European Conference on Speech Communication and Technology, September 3-7 2001, Aalborg, Denmark Details BibTeX DOI
714	Wellekens, Christian J Outils de navigation dans les fichiers audio RJC'2001, Rencontres des Jeunes Chercheurs , Septembre 2001, Mons, Belgique Details BibTeX
773	Nguyen, Patrick;Rigazio, Luca;Kuhn, Roland;Junqua, Jean-Claude;Wellekens, Christian J Self-adaptation using eigenvoices for large-vocabulary continuous speech recognition ITRW'2001, Adaptation Methods for Automatic Speech Recognition, August 2001 - Sophia-Antipolis, France Details BibTeX DOI
946	Wellekens, Christian J The ISCA technical and research workshop : adaptation methods in automatic speech recognition, Sophia-Antipolis, France The Phonetician, Number 84, 2001-II, International Society of Phonetic Sciences , pp 50-53 Details BibTeX
711	Wellekens, Christian J Seamless navigation in audio files Odyssey'2001: a speaker odyssey, June 18-22, 2001, Crete, Greece Details BibTeX DOI
Eurecom Reference	2000
566	Delacourt, Perrine;Wellekens, Christian J Regroupement par locuteur de messages vocaux CORESA'2000 : COmpression et REpresentation des Signaux Audiovisuels, 19-20 Octobre 2000, Poitiers, France Details BibTeX
564	Delacourt, Perrine;Wellekens, Christian J DISTBIC : A speaker-based segmentation for audio data indexing Speech Communication, Volume 32 N°1-2 -2000 , pp 111-126 Details BibTeX DOI
263	Bonastre, Jean-François;Delacourt, Perrine;Fredouille, Corinne;Merlin, Teva;Wellekens, Christian J A speaker tracking system based on speaker turn detection for NIST evaluation ICASSP 2000, 25th IEEE International conference on acoustic, speech and signal, June 5-9, 2000 - Istanbul, Turkey Details BibTeX DOI
448	Nguyen, Patrick;Kuhn, Roland;Junqua, Jean-Claude;Niedzielski, Nancy;Wellekens, Christian J Eigenvoices : a compact representation of speakers in a model space Annales des télécommunications, Volume 55 N°3-4 Mars-avril 2000 , pp 163-171 Details BibTeX DOI
269	Bonastre, Jean-François;Delacourt, Perrine;Fredouille, Corinne;Meignier, Sylvain;Merlin, Teva;Wellekens, Christian J Différentes stratégies pour le suivi de locuteur RFIA'2000, Reconnaissance des Formes et Intelligence Artificelle, February 1-3, 2000, Paris, France Details BibTeX File request
Eurecom Reference	1999
247	Wellekens, Christian J;Castaing, Pascale L 'internationalisation par les télécommunications et pour les télécommunications Journées des Techniques de l’Information et de la Communication, November 1999 - Nice, France Details BibTeX
254	Delacourt, Perrine;Wellekens, Christian J A first step into speaker-based indexing CBMI’99, 1st European Workshop on Content-Based Multimedia Indexing, October 25-27 1999, Toulouse, France Details BibTeX
250	Nguyen, Patrick;Wellekens, Christian J;Junqua, Jean-Claude Maximum likelihood eigenspace and MLLR for speech recognition in noisy environments Eurospeech'99 , ISCA conference on Speech Communication and Technology, 4-10 September 1999, Budapest, Hungary , pp 2519-2522 Details BibTeX DOI
177	Delacourt, Perrine;Kryze, David;Wellekens, Christian J Detection of speaker changes in an audio document Eurospeech'99 , ISCA conference on Speech Communication and Technology, 4-10 September 1999, Budapest, Hungary Details BibTeX DOI
259	Wellekens, Christian J Amélioration des taux de reconnaissance par filtrage de données CORESA'99, 5èmes journées d'téudes et d'échanges COmpression et REprésentation des Signaux Audiovisuels - June 14,-15, 1999, Sophia-Antipolis, France Details BibTeX
260	Nguyen, Patrick;Kuhn, Roland;Junqua, Jean-Claude;Niedzielski, Nancy;Wellekens, Christian J Voix propres: Une représentation compacte de locuteurs dans l'espace des modèles CORESA'99, 5èmes journées d'téudes et d'échanges COmpression et REprésentation des Signaux Audiovisuels - June 14,-15, 1999, Sophia-Antipolis, France Details BibTeX
178	Delacourt, Perrine;Wellekens, Christian J Audio data indexing : use of second order statistics for speaker-based segmentation ICMCS'99 - IEEE International Conference on Multimedia Computing and Systems, June 7-11, 1999, Florence, Italy Details BibTeX DOI
212	Delacourt, Perrine;Wellekens, Christian J Segmentation en locuteurs d'un document audio CORESA'99, 5èmes journées d'études et d'échanges COmpression et REprésentation des Signaux Audiovisuels - June 14,-15, 1999, Sophia-Antipolis, France Details BibTeX
176	Delacourt, Perrine;Kryze, David;Wellekens, Christian J Speaker-based segmentation for audio data indexing ISCA Workshop on accessing information in audio data, April 19-20, 1999 - Cambridge, UK Details BibTeX DOI
Eurecom Reference	1998
180	Wellekens, Christian J;Kangasharju, Jussi;Milesi, C The use of Meta-HMM in multistream HMM training for automatic speech recognition ICSLP'98 : 5th International Conference on Spoken Language Processing, 30 November-4 December 1998, Sydney, Australia , pp 2991-2994 Details BibTeX DOI
181	Wellekens, Christian J Enhanced ASR by acoustic feature filtering ICSLP'98 : 5th International Conference on Spoken Language Processing, 30 November-4 December 1998, Sydney, Australia , pp 2995-2998 Details BibTeX DOI
179	Wellekens, Christian J Introduction to speech recognition using neural networks ESANN'98, 6th European Symposium on Artificial Neural Networks, April 22-24, 1998 - Brussels, Belgium , pp 227-236 Details BibTeX DOI
Eurecom Reference	1997
512	Gelin, Philippe;Wellekens, Christian J Keyword spotting for multimedia document indexing SPIE'97, SPIE's International Symposium and Education Program on Voice, Video, and Data Communications, November 1997 - Dallas, USA Details BibTeX
554	Gelin, Philippe;Wellekens, Christian J REMAP for video soundtrack indexing ICASSP' 97, 22nd IEEE international conference on acoustics, speech, and signal processing, April 21-24 1997, Munich, Germany , pp 1423- 1426 Details BibTeX DOI
Eurecom Reference	1996
577	Gelin, Philippe; Wellekens, Christian J Keyword spotting enhancement for video soundtrack indexing ICSLP'96, IEEE 4th International Conference on Spoken Language - October 3-6, 1996 - Philadelphia, USA , pp 586-589 Details BibTeX DOI
442	Gelin, Philippe;Wellekens, Christian J Keyword spotting for video soundtrack indexing ICASSP'96, 21st IEEE international conference on acoustics, speech, and signal proceedings, May 7-10 1996, Atlanta, USA , pp 299-302 Details BibTeX DOI
Eurecom Reference	1993
732	Wellekens, Christian J Improved hidden Markov models for speech recognition through neural network learning Rapport de recherche RR-94-016 Details BibTeX
2138	Wellekens, Christian J Improved hidden Markov models for speech recognition through neural network learning From statistics to neural networks : theory and pattern recognition applications, June 21-July 2, 1993, Les Arcs, France Details BibTeX