A computational model of perceptuo-motor processing in speech perception: learning to imitate and categorize synthetic CV syllables

Raphaël Laurent 1, 2, 3, * Jean-Luc Schwartz 2 Pierre Bessière 1, 4, * Julien Diard 3
* Corresponding author
1 E-MOTION - Geometry and Probability for Motion and Action
Inria Grenoble - Rhône-Alpes, LIG - Laboratoire d'Informatique de Grenoble
2 GIPSA-PCMD - PCMD
GIPSA-DPC - Département Parole et Cognition
Abstract : This paper presents COSMO, a Bayesian computational model, which is expressive enough to carry out syllable production, perception and imitation tasks using motor, auditory or perceptuo-motor information. An imitation algorithm enables to learn the articulatory-to-acoustic mapping and the link between syllables and correspond- ing articulatory gestures, from acoustic inputs only: syn- thetic CV syllables generated with a human vocal tract model. We compare purely auditory, purely motor and perceptuo-motor syllable categorization under various noise levels.
Liste complète des métadonnées

Cited literature [29 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00827885
Contributor : Raphaël Laurent <>
Submitted on : Wednesday, May 29, 2013 - 6:36:31 PM
Last modification on : Thursday, February 7, 2019 - 4:31:14 PM
Document(s) archivé(s) le : Tuesday, April 4, 2017 - 1:12:24 PM

File

Laurent_COSMO_processing_sylla...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00827885, version 1

Citation

Raphaël Laurent, Jean-Luc Schwartz, Pierre Bessière, Julien Diard. A computational model of perceptuo-motor processing in speech perception: learning to imitate and categorize synthetic CV syllables. 14th Annual Conference of the International Speech Communication Association (Interspeech 2013), Aug 2013, Lyon, France. pp.2797-2801. ⟨hal-00827885⟩

Share

Metrics

Record views

1163

Files downloads

197