Laws for lips, Speech Communication, vol.5, issue.1, pp.97-104, 1986. ,
Modelling lip constriction anticipatory behaviour for rounding in french with the movement expansion model, Proceedings of the International Congress of Phonetic Sciences, vol.4, pp.152-155, 1995. ,
Multi-modal person veri cation tools using speech and images, Proceedings of the European Conference on Multimedia Applications, pp.747-761, 1996. ,
Audio-visual speech recognition compared across two architectures, Proceedings of the European Conference on Speech Communication and Technology (EUROSPEECH), vol.2, pp.1563-1566, 1995. ,
On the integration of auditory and visual parameters in a HMM-based ASR, Speechreading by Humans and Machines, vol.150, pp.461-473, 1996. ,
Reconnaissance automatique de la parole audiovisuelle, 1997. ,
Asynchronous integration of visual information in an automatic speech recognition system, Proceedings of the International Conference on Speech and Language Processing, vol.1, pp.34-37, 1996. ,
URL : https://hal.archives-ouvertes.fr/hal-01437232
Maximum mutual information estimation of hidden markov models parameters, International Conference on Acoustics, Speech and Signal Processing, pp.49-52, 1986. ,
Stochastic modelling for automatic speech understanding, Speech Recognition, pp.512-542, 1975. ,
DOI : 10.1016/b978-0-08-051584-7.50028-0
Subband approach for automatic speaker recognition : Optimal division of the frequency domain, Audioand Video-based Biometric Person Authentication, pp.196-202, 1997. ,
Expert conciliation for multi modal person authentication systems by bayesian statistics, Audio-and Video-based Biometric Person Authentication, pp.291-300, 1997. ,
Discriminative features selection for speech recognition, Computer Speech and Language, vol.7, pp.229-246, 1993. ,
DOI : 10.1006/csla.1993.1012
A new ASR approach based on independant processing and recombination of partial frequency bands, Proceedings of the International Conference on Speech and Language Processing, vol.1, pp.426-429, 1996. ,
DOI : 10.1109/icslp.1996.607145
Improving connected letter recognition by lipreading, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, vol.1, pp.557-560, 1993. ,
DOI : 10.1109/icassp.1993.319179
URL : http://isl.anthropomatik.kit.edu/downloads/Improving_Connected_Letter_Recognition_by_Lipreading.pdf
Eigenlips for robust speech recognition, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, vol.2, pp.669-672, 1994. ,
DOI : 10.1109/icassp.1994.389567
Probabilistic interpretation of feedforward classi cation network outputs with relationships to statistical pattern recognition, Neuro-Computing : Algorithms, Architectures and Applications, NATO ASI Series in Systems and Computer Science, 1989. ,
Automatic speech recognition that includes visual speech clues, Proceedings of the Institute of Acoustics, vol.16, pp.15-22, 1994. ,
Using the visual component in automatic speech recognition, Proceedings of the International Conference on Speech and Language Processing, vol.4, pp.1656-1659, 1996. ,
DOI : 10.1109/icslp.1996.607943
URL : http://www.asel.udel.edu/icslp/cdrom/vol3/999/a999.pdf
A family of parallel hidden markov models, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, vol.1, pp.377-380, 1992. ,
Person identi cation using multiple cues, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.17, issue.10, pp.955-966, 1995. ,
DOI : 10.1109/34.464560
Congurational vs. temporal coherence in audiovisual speech perception, Proceedings of the International Congress of Phonetic Sciences, vol.3, pp.218-221, 1995. ,
Human and machine recognition of faces : A survey, Proceedings IEEE, vol.83, issue.5, pp.705-740, 1995. ,
Voice and facial image integration for person identi cation, Multimedia Technologies and Future Applications, pp.155-161, 1993. ,
Integration of acoustic and visual speech for speaker recognition, Speech Communication and Technology, vol.1, pp.157-160, 1993. ,
Swiss french polyphone and polyvar : Telephone speech databases to study intra and inter speaker variability, IDIAP, 1995. ,
Maximum mutual information estimation of HMM parameters for continuous speech recognition using the N-BEST algorithm, Proceedings of Int. Conf. on Acoustics, Speech and Signal Processing, pp.701-704, 1990. ,
Use of active shape models for locating structures in medical images, Image and Vision Computing, vol.12, issue.6, pp.355-365, 1994. ,
Speaker independent bimodal phonetic recognition experiments, Proceedings of the International Conference on Speech and Language Processing, vol.1, pp.54-57, 1996. ,
DOI : 10.1109/icslp.1996.607023
URL : http://www.asel.udel.edu/icslp/cdrom/vol1/075/a075.pdf
Bimodal recognition experiments with recurrent neural networks, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, vol.2, pp.553-556, 1994. ,
DOI : 10.1109/icassp.1994.389596
An Introduction to Numerical Methods and Optimization Techniques, 1978. ,
Codebook weights adaptation for discriminative training of SCHMM-based speech recognition systems, Proceedings of European Conf. on Speech Communication and Technology, pp.93-96, 1995. ,
SESAM : A biometric person identi cation system using sensor fusion, Pattern Recognition Letters, vol.18, issue.9, pp.827-833, 1997. ,
DOI : 10.1016/s0167-8655(97)00063-9
Person authentication by fusing face and speech information, Audio-and Video-based Biometric Person Authentication, pp.311-318, 1997. ,
DOI : 10.1007/bfb0016010
Person recognition using acoustic and visual cues, Proceeding of the ESCA Workshop on Automatic Speaker Recognition, identi cation and Veri cation, pp.71-74, 1994. ,
Automatic optically-based recognition of speech, Pattern Recognition Letters, vol.8, issue.3, pp.159-164, 1988. ,
DOI : 10.1016/0167-8655(88)90094-3
An overview of speaker recognition technology, Proceedings of the ESCA Workshop on Automatic Speaker Recognition Identi cation Veri cation, pp.1-9, 1994. ,
DOI : 10.1007/978-1-4613-1367-0_2
URL : http://t2r2.star.titech.ac.jp/rrws/file/CTT100589789/ATD100000413/
An improved approach to the hidden markov model decomposition of speech and noise, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, vol.1, pp.233-236, 1992. ,
Combining methods to improve speaker veri cation decision, Proceedings of the International Conference on Speech and Language Processing, vol.3, pp.1756-1759, 1996. ,
DOI : 10.1109/icslp.1996.607968
URL : http://www.asel.udel.edu/icslp/cdrom/vol3/285/a285.pdf
Continuous optical speech recognition by lipreading, Proceedings of the 28th Conference on Signals, Systems and Computer, pp.572-577, 1994. ,
DOI : 10.1007/978-94-015-8935-2_14
Locating faces and facial parts, Proceedings of the International Workshop on Automatic Face and Gesture Recognition, vol.1, pp.41-46, 1995. ,
Optimization of speech parameter weighting for CDHMM word recognition, Proceedings of European Conf. on Speech Communication and Technology, pp.105-108, 1995. ,
Maximum likelihood weighting of dynamic speech features for CDHMM speech recognition, Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, vol.2, pp.1267-1270, 1997. ,
DOI : 10.1109/icassp.1997.596176
Hidden markov models merging acoustic and articulatory information to automatic speech recognition, Proceedings of the International Conference on Speech and Language Processing, vol.4, pp.2313-2315, 1996. ,
DOI : 10.1109/icslp.1996.607270
URL : http://www.asel.udel.edu/icslp/cdrom/vol4/307/a307.pdf
Speech recognition by statistical methods, Proceedings of the IEEE, vol.64, pp.532-556, 1976. ,
Asynchronie dans les syst emes de reconnaissance de la parole bas es sur les hmm, XXIes Journ ees d' Etude de la Parole, vol.1, pp.351-354, 1996. ,
Audiovisual speech recognition using the fuzzy shape lters model, Proceedings of the European Conference on Speech Communication and Technology (EUROSPEECH), vol.1, pp.307-310, 1995. ,
Combining evidence in multimodal personal identity recognition systems, Audioand Video-based Biometric Person Authentication, pp.327-334, 1997. ,
DOI : 10.1007/bfb0016012
Un poste \visage-parole" couleur, 1991. ,
Locating and tracking facial speech features, Proceedings of the International Conference on Pattern Recognition, pp.652-656, 1996. ,
Speaker identi cation by lipreading, Proceedings of the International Conference on Speech and Language Processing, vol.1, pp.62-65, 1996. ,
Lip-motion analysis for speech segmentation in noise, Speech Communication, vol.14, issue.3, pp.279-296, 1994. ,
Audiovisual speech recognition using multiscale nonlinear image decomposition, Proceedings of the International Conference on Speech and Language Processing, vol.1, pp.38-41, 1996. ,
Adaptative bimodal sensor fusion for automatic speechreading, International Conference on Acoustics, Speech and Signal Processing, vol.2, pp.833-837, 1996. ,
, Applications multimodales pour interfaces et bornes evolu ees, Ecole Th ematique : Traitement automatique de la parole : Fondements et Perspectives, vol.1, pp.155-164, 1995.
Channel separability in audiovisual integration of speech : A bayesian approach, Speechreading by Humans and Machines, Models, Systems and Applications, vol.150, pp.473-488, 1995. ,
The downhill simplex method, Computer Journal, vol.7, pp.391-398, 1965. ,
On the probabilistic interpretation of neural network classi ers and discriminative training, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.17, issue.2, pp.107-119, 1995. ,
On the estimation of \small" probabilities by leaving-oneout, IEEE Transaction on Pattern Analysis and Machine Intelligence, vol.17, issue.12, pp.1202-1212, 1995. ,
Neural networks, maximum mutual information training, and maximum likelihood training, International Conference on Acoustics, Speech and Signal Processing, pp.493-496, 1990. ,
High-performance connected digit recognition using maximum mutual information estimation, IEEE Trans. on SAP, vol.2, issue.2, pp.299-311, 1994. ,
The image input microphone { a new nonacoustic speech communication system by media conversion from oral motion images to speech, IEEE Journal on Selected areas in Communications, vol.13, issue.1, pp.42-48, 1995. ,
An improved automatic lipreading system to enhance speech recognition, 1987. ,
Automatic Lipreading to Enhance Speech Recognition, 1984. ,
The m2vts multimodal face database (release 1.00), Audio-and Video-based Biometric Person Authentication, pp.403-409, 1997. ,
Speaker independent audio-visual database for bimodal ASR, Proceedings of the Audio-Visual Speech Processing workshop, ESCA ISSN # 1018, vol.4554, pp.65-68, 1997. ,
Auditory, visual and audiovisual vowel representation : Experiments and modelling, Proceedings of the International Congress of Phonetic Sciences, vol.3, pp.114-121, 1995. ,
Mod eles d'Int egration audio-visuelle de signaux linguistiques : de la perception humaine a la reconnaissance automatique de voyelles, 1995. ,
Learning state-dependent stream weights for multi-codebook HMM speech recognition systems, Proceedings of Int. Conf. on Acoustics, Speech and Signal Processing, pp.349-352, 1990. ,
Adaptative determination of audio and visual weights for automatic speech recognition, Proceedings of the Audio-Visual Speech Processing workshop, ESCA ISSN # 1018, vol.4554, pp.61-64, 1997. ,
Audio-visual sensory integration using hidden markov models, Speechreading by Humans and Machines, vol.150, pp.489-497, 1996. ,
Sensory integration in audiovisual automatic speech recognition, Conference Record of the Twenty-Eighth Asilomar Conference on Signal, Systems and Computers, pp.561-565, 1994. ,
Articulatory characteristics of lip shape during the production of japanese, Proceedings of the International Conference on Spoken Language Processing, vol.1, pp.441-444, 1990. ,
Robust audiovisual integration using semicontinuous hidden markov models, Proceedings of the International Conference on Speech and Language Processing, vol.1, pp.42-45, 1996. ,
Subband-based recognition of noisy speech, Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, vol.2, pp.1255-1258, 1997. ,
Integrating audio and visual information to provide highly robust speech recognition, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, vol.2, pp.821-824, 1996. ,
Modelling asynchrony in speech using elementary singlesignal decomposition, Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, vol.2, pp.1247-1250, 1997. ,
Hidden markov model decomposition of speech and noise, Proceedings of the International Conference on Acoustics, Speech and Signal Processing, pp.845-848, 1990. ,
, Principles of Digital Communication and Coding, 1979.
Multimodal learning interfaces, Proceedings of ARPA Spoken Language Technology Workshop, vol.1, 1995. ,
Multi-sensorial inputs for the identication of persons with synergic computers, Proceedings of the IEEE Int. Conf. on Image Processing, vol.2, pp.287-291, 1994. ,
Lip-reading of japanese vowels using neural networks, Proceedings of the International Conference on Spoken Language Processing, vol.2, pp.1373-1376, 1990. ,
Improvements in connected digit recognition using higher order spectral and energy features, Proceedings of Int. Conf. on Acoustics, Speech and Signal Processing, pp.349-352, 1991. ,
Lipreading by neural networks : Visual preprocessing, learning and sensory integration, Advances in Neural Information Processing Systems, vol.6, pp.1027-1034, 1994. ,
Neural network vowel-recognition jointly using voice features and mouth shape image, Pattern Recognition, vol.24, issue.10, pp.921-927, 1991. ,
HTK : Hidden Markov Model Toolkit V1, vol.5, 1993. ,
Neural network models of sensory integration for improved vowel recognition, Proceedings of the IEEE, vol.78, issue.10, pp.1658-1668, 1990. ,
Acoustic-labial speaker veri cation, Pattern Recognition Letters, vol.9, issue.18, pp.853-858, 1997. ,
DOI : 10.1016/s0167-8655(97)00070-6
, Congr es internationaux avec actes et comit e de lecture
Bimodal Speech Recognition, Proceedings of the International Workshop on Automatic Face and Gesture Recognition, vol.1, pp.320-325, 1995. ,
URL : https://hal.archives-ouvertes.fr/tel-02152912
Integrating visual and acoustic information in a speech recognition system based on HMM, Proceedings of the International Congress of Phonetic Sciences, vol.4, pp.288-291, 1995. ,
Handling the disynchronization phenomena with HMM in connected speech, Proceedings of the VIII European Signal Processing Conference, vol.1, pp.133-136, 1996. ,
Acoustic-labial speaker veri cation, Audio-and Video-based Biometric Person Authentication, pp.319-326, 1997. ,
Integrating Acoustic and Labial Information for Speaker Identi cation and Veri cation, Proceedings of the European Conference on Speech Communication and Technology (EUROSPEECH), pp.1599-1602, 1997. ,
Word-Dependent Acoustic-Labial Weights in HMMBased Speech Recognition, Proceedings of the ESCA/ESOP Workshop on Audio-Visual Speech Processing, pp.69-72, 1997. ,
Estimating Acoustic-labial Weights in Connected Speech Recognition Systems Based on HMM, Proceedings of IEEE Int. Conf. on Systems, Man, and Cybernetics, 1997. ,
,
Asynchronie dans les syst emes de reconnaissance de la parole bas es sur les HMM, XXIes Journ ees d' Etude de la Parole, vol.1, pp.351-354, 1996. ,
, , 1995.
, Applications multimodales pour interfaces et bornes evolu ees, Ecole Th ematique : Traitement automatique de la parole : Fondements et Perspectives, vol.1, pp.155-164
V eri cation Multimodale de l'Identit e d'une Personne, 1997. ,
, , vol.8, p.99
, , vol.76, p.97
, , vol.31, p.105
, , vol.10, p.105
, , vol.86, p.101
, , vol.38, p.100
, , vol.38, p.97
, , vol.37, p.98
, , vol.101, p.105
, , vol.77, p.101
, , vol.34, p.105
, , vol.16, p.98
, , vol.76, p.97
, , vol.33, p.98
, , vol.33, p.100
, , vol.84, p.100
, , vol.50, p.102
, , vol.53, p.112
, , vol.38, p.98
, , vol.50, p.102
, , vol.16, p.98
, , vol.16, p.98
, , vol.56, p.97
, , vol.12, p.105
, , vol.38, p.98
, , vol.26, p.105
, , vol.38, p.97
, , vol.15, p.98
, , vol.35, p.100
, , vol.52, p.104
, , vol.27, p.103
, , vol.38, p.102
, , vol.22, p.104
, , vol.51, p.105
, , vol.53, p.112
, , vol.38, p.102
, , vol.8, p.99
, , vol.51, p.102
, , vol.79, p.99
, , vol.51, p.100
, , p.99
, , vol.76, p.100
, , vol.38, p.99
, , vol.85, p.99
, , vol.85, p.99
, , vol.51, p.99
, , vol.79, p.99
, , vol.51, p.102
, , vol.51, p.105
, , vol.101, p.105
, , vol.44, p.99
, , vol.38, p.100
, , vol.10, p.105
, , vol.38, p.100
, , vol.15, p.102
, , vol.38, p.97
, , vol.52, p.104
, , vol.33, p.100
, , vol.34, p.114
, , vol.99, p.105
, , vol.16, p.98
, , vol.53, p.112
, , vol.10, p.103
, , vol.35, p.100
, , vol.27, p.103
, , vol.99, p.105
, , vol.50, p.100
, , vol.33, p.100
, , vol.85, p.100
, , vol.15, p.100
, , vol.52, p.105
, , vol.76, p.100
, , vol.38, p.100
, , vol.15, p.98
, , vol.52, p.105
, , vol.51, p.104
, , vol.51, p.102
, , vol.84, p.100
, , vol.51, p.102
, , vol.79, p.99
, , vol.51, p.104
, , vol.53, p.112
, , vol.16, p.103
, , vol.38, p.100
, , vol.38, p.100
, , vol.12, p.105
, , vol.79, p.99
, , vol.52, p.104
, , vol.12, p.105
, , vol.37, p.101
, , vol.51, p.104
, , vol.27, p.112
, , vol.36, p.105
, , vol.52, p.104
, , vol.33, p.101
, , vol.51, p.104
, , vol.52, p.98
, , vol.51, p.103
, , vol.52, p.104
, , vol.8, p.101
, , vol.53, p.112
, , vol.85, p.99
, , vol.40, p.104
, , vol.53, p.112
, , vol.33, p.101
, , vol.76, p.97
, , vol.77, p.112
, , vol.76, p.97
, , vol.86, p.101
, , vol.12, p.105
, , p.99
, , vol.33, p.101
, , vol.101, p.105
, , vol.36, p.100
, , vol.44, p.102
, , vol.34, p.104
, , vol.38, p.97
, , vol.51, p.99
, , vol.52, p.104
, , vol.8, p.99
, , vol.53, p.112
, , vol.38, p.100
, , vol.50, p.100
, , vol.15, p.104
, , vol.27, p.103
, , vol.51, p.103
, , vol.51, p.102
, , vol.44, p.102
, , vol.39, p.102
, , vol.38, p.102
, , vol.38, p.102
, , vol.53, p.112
, , vol.52, p.104
, , vol.15, p.98
, , vol.38, p.104
, , vol.51, p.102
, , vol.53, p.112
, , vol.100, p.105
, , vol.76, p.102
, , vol.76, p.97
, , vol.92, p.100
, , vol.52, p.102
, , vol.51, p.104
, , vol.40, p.104
, , vol.33, p.101
, , vol.10, p.103
, , vol.52, p.102
, , vol.41, p.103
, , vol.10, p.105
, , vol.26, p.105
, , vol.92, p.100
, , vol.10, p.103
, , vol.51, p.104
, , vol.12, p.105
, , vol.34, p.105
, , vol.38, p.102
, , vol.79, p.99
, , vol.76, p.97
, , vol.51, p.103
, , vol.51, p.104
, , vol.34, p.105
, , vol.79, p.99
, , vol.52, p.104
, , vol.77, p.101
, , vol.16, p.103
, , vol.26, p.105
, , vol.51, p.105
, , vol.76, p.102
, , vol.15, p.104
, , vol.38, p.104
, , vol.52, p.104
, , vol.52, p.104
, , vol.12, pp.103-105
, , vol.51, p.104
, , vol.38, p.104
, , vol.79, p.99
, , vol.51, p.104
, , vol.34, p.101
, , vol.22, p.104
, , vol.52, p.104
, , vol.52, p.104
, , vol.15, p.104
, , vol.51, p.104
, Remerciements et responsabilit es
, e absolument impossible de suivre ce chemin qui am ene quelqu'un a produire un tel document. Je vais donc ici partager ma responsabilit e en les d enon cant publiquement : Merci a ma grand-m ere, qui me soutient encore, malgr e ses 84 ans et mes 84 kilos. Merci a mes parents qui n'ont jamais perdu l'espoir de faire quelque chose de moi, Sans le support d'un nombre consid erable de gens, il m'aurait et
Merci a Steph pour notre longue cohabitation paci que. Merci a Philou pour ses renseignements g en ereux. Merci a Thierry pour la protection contre la d ebauche. Merci a Fred a Felipe pour l'apprentissage du dur m etier de conf erencier international. Merci a Je pour nos discussions constructives. Merci a Pascal pour les collaborations fructueuses, Merci a R egis pour sa bonne humeur in ebranlable. Merci a Thierry pour les cours de m edecine sportive. Merci a Laurence et Vilou pour leur compagnie pendant les courses. Merci a Jocelyne pour les voyages. Merci a Corine. Merci a Jean-luc de m'avoir accept e dans son laboratoire. Merci a Gilbert de m'avoir accept e dans son equipe. Merci a J urgen pour les mod eles d eformables et la vie nocturne de Martigny-Ville. Merci a Gilles pour les voyages a Martigny-Bourg. Merci a C edric pour les excursions a MartignyCombes. Merci a Georg pour les rencontres des Alpes. Merci a Tomas pour l'Absolut ,
, Merci a S everine pour les danses latines. Merci a Sylvie pour les danses tropicales. Merci a Fabienne pour les danses folkloriques. Merci a Philippe pour s'enêtre sorti et moi avec. Merci a Linda-Chantal pour son amour. Thanks to CUED and CUCL people for their welcome. Thanks to SWP. Thanks to Miles for his moral support in public houses, Merci a Pierrot-Yves pour les soir ees guitare et les petits d ejeuners au Remerciements Guronzan. Merci a Laurent pour le coup de l salutaire