A visual speech recognition system for an ultrasound-based silent speech interface  - MAGIC
Communication Dans Un Congrès Année : 2011

A visual speech recognition system for an ultrasound-based silent speech interface 

Résumé

The development of a continuous visual speech recognizer for a silent speech interface has been investigated using a visual speech corpus of ultrasound and video images of the tongue and lips. By using high-speed visual data and tied-state cross-word triphone HMMs, and including syntactic information via domain-specific language models, word-level recognition accuracy as high as 72% was achieved on visual speech. Using the Julius system, it was also found that the recognition should be possible in nearly real-time.

Domaines

Linguistique
Fichier non déposé

Dates et versions

halshs-00683754 , version 1 (29-03-2012)

Identifiants

  • HAL Id : halshs-00683754 , version 1

Citer

Jun Cai, Thomas Hueber, Bruce Denby, Elie-Laurent Benaroya, Gérard Chollet, et al.. A visual speech recognition system for an ultrasound-based silent speech interface . ICPhS 2011 - 17th International Congress of Phonetic Sciences, Aug 2011, Hong Kong, China. pp.384-387. ⟨halshs-00683754⟩
382 Consultations
0 Téléchargements

Partager

More