Belief Hidden Markov Model for speech recognition

Abstract : Speech Recognition searches to predict the spoken words automatically. These systems are known to be very expensive because of using several pre-recorded hours of speech. Hence, building a model that minimizes the cost of the recognizer will be very interesting. In this paper, we present a new approach for recognizing speech based on belief HMMs instead of proba-bilistic HMMs. Experiments shows that our belief recognizer is insensitive to the lack of the data and it can be trained using only one exemplary of each acoustic unit and it gives a good recognition rates. Consequently, using the belief HMM recognizer can greatly minimize the cost of these systems.
Type de document :
Communication dans un congrès
International Conference on Modeling, Simulation and Applied Optimization (ICMSAO), Apr 2013, Hammamet, Tunisia. pp.1 - 6, 2013, 〈10.1109/ICMSAO.2013.6552563〉
Liste complète des métadonnées

Littérature citée [13 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01108027
Contributeur : Arnaud Martin <>
Soumis le : jeudi 22 janvier 2015 - 09:44:57
Dernière modification le : mercredi 2 août 2017 - 10:09:10
Document(s) archivé(s) le : jeudi 23 avril 2015 - 10:11:31

Fichiers

articleV05.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Siwar Jendoubi, Boutheina Ben Yaghlane, Arnaud Martin. Belief Hidden Markov Model for speech recognition. International Conference on Modeling, Simulation and Applied Optimization (ICMSAO), Apr 2013, Hammamet, Tunisia. pp.1 - 6, 2013, 〈10.1109/ICMSAO.2013.6552563〉. 〈hal-01108027〉

Partager

Métriques

Consultations de
la notice

143

Téléchargements du document

59