Dynamic Bayesian Networks for Automatic Speech Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2002

Dynamic Bayesian Networks for Automatic Speech Recognition

Résumé

State-of-the-art automatic speech recognition (ASR) systems are based on probabilistic modelling of the speech signal using Hidden Markov Models. The limitations of these systems under real life conditions arose a question about the robustness of the underlying acoustic modelling methodology. The scope of my thesis is to explore the formalism of Probabilistic Graphical Models, particularly Dynamic Bayesian Networks, from a theoretical and practical point of view, with the aim of developing reliable models of speech and of developing robust ASR systems.
Fichier non déposé

Dates et versions

inria-00100856 , version 1 (26-09-2006)

Identifiants

  • HAL Id : inria-00100856 , version 1

Citer

Murat Deviren. Dynamic Bayesian Networks for Automatic Speech Recognition. Eighteenth National Conference on Artificial Intelligence, AAAI 2002, SIGART/AAAI Doctoral Consortium, Jul 2002, Edmonton, Alberta, Canada, 1 p. ⟨inria-00100856⟩
55 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More