Class-based speech recognition using a maximum dissimilarity criterion and a tolerance classification margin

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 : One of the difficult problems of Automatic Speech Recognition (ASR) is dealing with the acoustic signal variability. Much state-of-the-art research has demonstrated that splitting data into classes and using a model specific to each class provides better results. However, when the dataset is not large enough and the number of classes increases, there is less data for adapting the class models and the performance degrades. This work extends and combines previous research on unsupervised splits of datasets to build maximally separated classes and the introduction of a tolerance classification margin for a better training of the class model parameters. Experiments, carried out on the French radio broadcast ESTER2 data, show an improvement in recognition results compared to the ones obtained previously. Finally, we demonstrate that combining the decoding results from different class models leads to even more significant improvements.
Type de document :
Communication dans un congrès
SLT 2012 - 4th IEEE Workshop on Spoken Language Technology, Dec 2012, Miami, United States. 2012
Liste complète des métadonnées

https://hal.inria.fr/hal-00753454
Contributeur : Denis Jouvet <>
Soumis le : lundi 19 novembre 2012 - 11:27:26
Dernière modification le : jeudi 11 janvier 2018 - 06:25:24

Identifiants

  • HAL Id : hal-00753454, version 1

Collections

Citation

Arseniy Gorin, Denis Jouvet. Class-based speech recognition using a maximum dissimilarity criterion and a tolerance classification margin. SLT 2012 - 4th IEEE Workshop on Spoken Language Technology, Dec 2012, Miami, United States. 2012. 〈hal-00753454〉

Partager

Métriques

Consultations de la notice

183