Skip to Main content Skip to Navigation
Theses

Systèmes de reconnaissance de la parole revisités : réseaux bayésiens dynamiques et nouveaux paradigmes

Abstract : In this thesis we focus on four principle components of a speech recognition system: acoustic modeling, language modeling, speech feature extraction and noise compensation. We propose novel modeling approaches for acoustic and linguistic modeling within the Bayesian networks formalism. Bayesian networks are a subset of probabilistic graphical models that include the most widely used probability models in speech recognition. Therefore rethinking the modeling problems in this formalism provides new perspectives that were not considered previously. Besides novel modeling approaches we also address new speech feature extraction schemes. Our main motivation in this direction is to seek for robust features that are not bound to be used in classical hidden Markov modeling (HMM) approach. Finally, we address the robustness problem for varying application conditions and propose a novel supervised compensation scheme.
Document type :
Theses
File URL :
http://docnum.univ-lorraine.fr/prive/SCD_T_2004_0161_DEVIREN.pdf
Complete list of metadata

https://hal.univ-lorraine.fr/tel-01746769
Contributor : Thèses Ul <>
Submitted on : Thursday, March 29, 2018 - 10:44:31 AM
Last modification on : Tuesday, September 1, 2020 - 3:21:06 PM

Identifiers

  • HAL Id : tel-01746769, version 1

Collections

Citation

Murat Deviren. Systèmes de reconnaissance de la parole revisités : réseaux bayésiens dynamiques et nouveaux paradigmes. Autre [cs.OH]. Université Henri Poincaré - Nancy 1, 2004. Français. ⟨NNT : 2004NAN10161⟩. ⟨tel-01746769⟩

Share

Metrics

Record views

20