Component Structuring and Trajectory Modeling for Speech Recognition

Arseniy Gorin 1 Denis Jouvet 1
1 PAROLE - Analysis, perception and recognition of speech
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : When the speech data are produced by speakers of different age and gender, the acoustic variability of any given phonetic unit becomes large, which degrades speech recognition performance. A way to go beyond the conventional Hidden Markov Model is to explicitly include speaker class information in the modeling. Speaker classes can be obtained by unsupervised clustering of the speech utterances. This paper introduces a structuring of the Gaussian compo- nents of the GMM densities with respect to speaker classes. In a first approach, the structuring of the Gaussian components is combined with speaker class-dependent mixture weights. In a second approach, the structuring is used with mixture transition matrices, which add dependencies between Gaussian components of mixture densities (as in stranded GMMs). The different approaches are evaluated and compared in detail on the TIDIGITS task. Significant improvements are obtained using the proposed approaches based on structured components. Additional results are reported for phonetic decoding on the NEOLOGOS database, a large corpus of French telephone data.
Type de document :
Communication dans un congrès
Interspeech, Sep 2014, Singapoore, Singapore. 2014
Liste complète des métadonnées

Littérature citée [17 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01063653
Contributeur : Arseniy Gorin <>
Soumis le : vendredi 12 septembre 2014 - 16:03:11
Dernière modification le : mardi 18 décembre 2018 - 16:38:02
Document(s) archivé(s) le : samedi 13 décembre 2014 - 10:46:34

Fichier

inter2014_agorin_v11.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01063653, version 1

Collections

Citation

Arseniy Gorin, Denis Jouvet. Component Structuring and Trajectory Modeling for Speech Recognition. Interspeech, Sep 2014, Singapoore, Singapore. 2014. 〈hal-01063653〉

Partager

Métriques

Consultations de la notice

837

Téléchargements de fichiers

142