How can acoustic-to-articulatory maps be constrained? - Archive ouverte HAL Access content directly
Conference Papers Year : 2008

How can acoustic-to-articulatory maps be constrained?

(1) , (2) , (3)
1
2
3

Abstract

The objective of the presentation is to examine issues in constraining acoustic-to-articulatory maps by means of facial data and other a priori knowledge regarding speech production. Constraints that are considered are the insertion of data on lip opening, spread and protrusion, as well as other facial data together with constraints on the vocal tract length. A priori knowledge that has been taken into account concerns the deformation and speed of deformation of the vocal tract as well as phonetic rules regarding vowel-typical tract shapes. Inverse maps that have been tested are formant-to-area and formant-to-parametric sagittal profile maps as well as audio/visualto- electromagnetic coil trajectory maps. The results obtained while mapping audio-only data compared to audio combined with other data are discussed.
Fichier principal
Vignette du fichier
1569105098.pdf (180.36 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00335958 , version 1 (31-10-2008)

Identifiers

  • HAL Id : inria-00335958 , version 1

Cite

Yves Laprie, Petros Maragos, Jean Schoentgen. How can acoustic-to-articulatory maps be constrained?. 16th European Signal Processing Conference - EUSIPCO 2008, Aug 2008, Lausanne, Switzerland. ⟨inria-00335958⟩
98 View
105 Download

Share

Gmail Facebook Twitter LinkedIn More