Continuous Articulatory-to-Acoustic Mapping using Phone-based Trajectory HMM for a Silent Speech Interface - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Continuous Articulatory-to-Acoustic Mapping using Phone-based Trajectory HMM for a Silent Speech Interface

Résumé

The article presents an HMM-based mapping approach for converting ultrasound and video images of the vocal tract into an audible speech signal, for a silent speech interface application. The proposed technique is based on the joint modeling of articulatory and spectral features, for each phonetic class, using Hidden Markov Models (HMM) and multivariate Gaussian distributions with full covariance matrices. The articulatory-toacoustic mapping is achieved in 2 steps: 1) finding the most likely HMM state sequence from the articulatory observations; 2) inferring the spectral trajectories from both the decoded state sequence and the articulatory observations. The proposed technique is compared to our previous approach, in which only the decoded state sequence was used for the inference of the spectral trajectories, independently from the articulatory observations. Both objective and perceptual evaluations show that this new approach leads to a better estimation of the spectral trajectories.
Fichier principal
Vignette du fichier
th_IS2012_silentspeech.pdf (492.9 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00741682 , version 1 (15-10-2012)

Identifiants

  • HAL Id : hal-00741682 , version 1

Citer

Thomas Hueber, Gérard Bailly, Bruce Denby. Continuous Articulatory-to-Acoustic Mapping using Phone-based Trajectory HMM for a Silent Speech Interface. Interspeech 2012 - 13th Annual Conference of the International Speech Communication Association, Sep 2012, Portland, United States. pp.Tue.P3c.01. ⟨hal-00741682⟩
356 Consultations
261 Téléchargements

Partager

Gmail Facebook X LinkedIn More