Acoustic-to-articulatory inversion using speech recognition and trajectory formation based on phoneme hidden Markov models - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2009

Acoustic-to-articulatory inversion using speech recognition and trajectory formation based on phoneme hidden Markov models

Résumé

In order to recover the movements of usually hidden articulators such as tongue or velum, we have developed a data-based speech inversion method. HMMs are trained, in a multistream framework, from two synchronous streams: articulatory movements measured by EMA, and MFCC + energy from the speech signal. A speech recognition procedure based on the acoustic part of the HMMs delivers the chain of phonemes and together with their durations, information that is subsequently used by a trajectory formation procedure based on the articulatory part of the HMMs to synthesise the articulatory movements. The RMS reconstruction error ranged between 1.1 and 2. mm.
Fichier principal
Vignette du fichier
aby_IS09.pdf (83.95 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00419227 , version 1 (23-09-2009)

Identifiants

  • HAL Id : hal-00419227 , version 1

Citer

Atef Ben Youssef, Pierre Badin, Gérard Bailly, Panikos Heracleous. Acoustic-to-articulatory inversion using speech recognition and trajectory formation based on phoneme hidden Markov models. Interspeech 2009 - 10th Annual Conference of the International Speech Communication Association, Sep 2009, Brighton, United Kingdom. pp.2255-2258. ⟨hal-00419227⟩
301 Consultations
457 Téléchargements

Partager

Gmail Facebook X LinkedIn More