HMM-based Vowel and Consonant Automatic Recognition in Cued Speech for French - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2009

HMM-based Vowel and Consonant Automatic Recognition in Cued Speech for French

Résumé

In this paper, hidden Markov models (HMM)-based vowel and consonant automatic recognition in French Cued Speech is presented. Cued Speech is a visual communication mode which uses handshapes in different positions and in combination with lip-patterns of speech, makes all the sounds of spoken language clearly understandable to deaf and hearingimpaired people. The aim of Cued Speech is to overcome the problems of lipreading and thus enable deaf children and adults to fully understand a spoken language. Previously, the authors have reported experimental results on vowel recognition in Cued Speech for French based on feature fusion and multi-stream HMM decision fusion. This study, further investigates the vowel recognition by considering vowel classes based on similarities on the lips. Also automatic consonant recognition experiments in Cued Speech for French are reported. The obtained results are promising and comparable with results obtained using audio signal.
Fichier principal
Vignette du fichier
vecims09.pdf (160.4 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00372700 , version 1 (02-04-2009)

Identifiants

  • HAL Id : hal-00372700 , version 1

Citer

Panikos Heracleous, Noureddine Aboutabit, Denis Beautemps. HMM-based Vowel and Consonant Automatic Recognition in Cued Speech for French. VECIMS 2009 - IEEE International Symposium on Virtual Environments, Human-Computer Interfaces and Measurement Systems (VECIMS), May 2009, Hong Kong, China. pp.1-4. ⟨hal-00372700⟩
174 Consultations
263 Téléchargements

Partager

Gmail Facebook X LinkedIn More