An elitist approach for extracting automatically well-realized speech sounds with high confidence - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2005

An elitist approach for extracting automatically well-realized speech sounds with high confidence

Résumé

This paper presents an ëlitist approach\" for extracting automatically well-realized speech sounds with high confidence. The elitist approach uses a speech recognition system based on Hidden Markov Models (HMM). The HMM are trained on speech sounds which are systematically well-detected in an iterative procedure. The results show that, by using the HMM models defined in the training phase, the speech recognizer detects reliably specific speech sounds with a small rate of errors.
Fichier principal
Vignette du fichier
Interspeech.pdf (60.68 Ko) Télécharger le fichier
Loading...

Dates et versions

hal-00014016 , version 1 (21-11-2005)

Identifiants

Citer

Jean-Baptiste Maj, Anne Bonneau, Dominique Fohr, Yves Laprie. An elitist approach for extracting automatically well-realized speech sounds with high confidence. 2005, pp.2925--2929. ⟨hal-00014016⟩
210 Consultations
104 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More