Reconnaissance parole And NotJ.-P. Martens
List of bibliographic references
Number of relevant bibliographic references: 46.Ident. | Authors (with country if any) | Title |
---|---|---|
000228 | Th. Meilender [France] ; Abdel Belaïd [France] | Segmentation of Continuous Document Flow by a modified Backward-Forward algorithm |
000404 | ZOUHOUR NEJI BEN SALEM [Tunisie] ; Laurent Bougrain [France] ; Frcdcric Alexandre [France] | Comparison between two spatio-temporal organization maps for speech recognition |
000556 | Christophe Cerisara [France] ; Luca Rigazio [États-Unis] ; Jean-Claude Junqua [États-Unis] | α-Jacobian environmental adaptation |
000699 | Murat Deviren [France] ; Khalid Daoudi [France] | Frequency and wavelet filtering for robust speech recognition |
000785 | Joseph Di Martino [France] | On the use of high order derivatives for high performance alphabet recognition |
000799 | YASSINE BEN AYED [France] ; Dominique Fohr [France] ; Jean Paul Haton [France] ; Gérard Chollet [France] | Keyword spotting using Support Vector Machines |
000810 | Christophe Cerisara [France] ; Jean-Claude Junqua [États-Unis] ; Luca Rigazio [États-Unis] | Dynamic estimation of a noise over estimation factor for Jacobian-based adaptation |
000828 | Khalid Daoudi [France] | Automatic speech recognition: The new millennium |
000924 | David Langlois [France] ; Kamel Smaïli [France] ; Jean-Paul Haton [France] | A new method based on context for combining statistical language models |
000936 | Jean-Paul Haton [France] | Reconnaissance automatique de la parole |
000A81 | M.-C. Haton [France] | Issues in using models for self evaluation and correction of speech |
000A93 | C. Cerisara [France] | Dealing with loss of synchronism in multi-band continuous speech recognition systems |
000A96 | Jean-Paul Haton [France] | Connectionist and hybrid models for automatic speech recognition |
000B25 | R. Sandrine [France] ; C. Noëlle [France] ; D. Pierre [France] | Etude empirique de l'usage du geste et de la parole dans une interface multimodale imposant des contraintes d'expression |
000B31 | H. Hermansky [États-Unis, République tchèque] | Should recognizers have ears? |
000B33 | B. E. D. Kingsbury [États-Unis] ; N. Morgan [États-Unis] ; S. Greenberg [États-Unis] | Robust speech recognition using the modulation spectrogram |
000B36 | M. J. F. Gales [Royaume-Uni] | Predictive model-based compensation schemes for robust speech recognition |
000B39 | C.-H. Lee [États-Unis] | On stochastic feature and model compensation approaches to robust speech recognition |
000B50 | P. W. Shields [Royaume-Uni] ; D. R. Campbell [Royaume-Uni] | Intelligibility improvements obtained by an enhancement method applied to speech corrupted by noise and reverberation |
000B53 | M. Omologo [Italie] ; P. Svaizer [Italie] ; M. Matassoni [Italie] | Environmental conditions and acoustic transduction in hands-free speech recognition |
000B54 | I. Illina [France] ; M. Afify [France] ; Y. Gong [États-Unis] | Environment normalization training and environment adaptation using mixture stochastic trajectory model |
000B57 | J. De Veth [Pays-Bas] ; L. Boves [Pays-Bas] | Channel normalization techniques for automatic speech recognition over the telephone |
000B58 | O. Viikki [Finlande] ; K. Laurila [Finlande] | Cepstral domain segmental feature vector normalization for noise robust speech recognition |
000B63 | B. L. Pellom [États-Unis] ; J. H. L. Hansen [États-Unis] | Automatic segmentation of speech recorded in unknown noisy channel characteristics |
000B69 | M. Afify [France] ; YIFAN GONG [États-Unis] ; Jean-Paul Haton [France] | A general joint additive and convolutive bias compensation approach applied to noisy lombard speech recognition |
000B73 | ||
000C07 | Y. Gong [France] | Stochastic trajectory modeling and sentence searching for continuous speech recognition |
000C17 | L. Djezzar [France] ; N. Pican [France] | Phonetic knowledge embedded in a context sensitive MLP for French speaker-independent speech recognition |
000C32 | I. Illina [France] ; Y. Gong [États-Unis] | Elimination of trajectory folding phenomenon : HMM, trajectory mixture HMM and mixture stochastic trajectory model |
000C42 | J.-F. Mari [France] ; Jean-Paul Haton [France] ; A. Kriouile [France] | Automatic word recognition based on second-order Hidden Markov models |
000C45 | M. Afify [France] ; Y. Gong [États-Unis] ; Jean-Paul Haton [France] | A unified maximum likelihood approach to acoustic mismatch compensation : Application to noisy lombard speech recognition |
000C98 | O. Siohan [France] ; Y. Gong [France] ; J. P. Haton [France] | Comparative experiments of several adaptation approaches to noisy speech recognition using stochastic trajectory models |
000C99 | J. P. Haton [France] | Comments on ""Towards increasing speech recognition error rates"" by H. Bourlard, H. Hermansky, and N. Morgan |
000D22 | Y. Gong [France] | Speech recognition in noisy environments: a survey |
000D24 | H. Li [France] ; J. P. Haton ; J. Su | Short-timed speech dynamics for speaker recognition |
000D41 | Jean-Paul Haton [France] | Problems and solutions for noisy speech recognition |
000D50 | Y. Gong [France] ; Jean-Paul Haton [France] | Plausibility functions in continuous speech recognition: The VINICS system |
000D63 | YIFAN GONG ; Jean-Paul Haton [France] | Signal-to-string conversion based on high likelihood regions using embedded dynamic programming |
000D67 | Jean-Marie Pierrel [France] ; N. Carbonell ; Jean-Paul Haton [France] ; K. Smaili | Vers une meilleure intégration de la parole dans des systèmes de communication homme-machine |
000D68 | J.-C. Junqua [France] | Utilisation d'un modèle d'audition et de connaissances phonétiques en reconnaissance automatique de la parole |
000D69 | Jean-Paul Haton [France] ; A. Bonneau ; D. Fohr ; Y. Laprie ; YIFAN GONG ; Jean-Marie Pierrel [France] | Décodage acoustico-phonétique : problèmes et éléments de solution |
000D73 | A. Gourinda ; J. P. Haton | Utilisation de la quantification vectorielle multi-sections en reconnaissance de mots isolés |
000D75 | F. Alexandre ; Y. Burnod ; F. Guyot ; Jean-Paul Haton [France] | La colonne corticale, nouvelle unité de base pour des réseaux multicouches |
000D78 | Jean-Paul Haton [France] | Les systèmes à bases de connaissances en reconnaissance et en interprétation de formes |
000D79 | Jean-Paul Haton [France] ; M.-C. Haton | Artificial intelligence techniques in man-machine communication |
000D82 | C. Pister-Bourjot ; Jean-Paul Haton [France] | Automatic learning: an approach to the adaptation of a speech recognition system to one or several speakers |
![]() | This area was generated with Dilib version V0.6.33. | ![]() |