INTERSPEECH 2013 14thAnnual Conference of the International Speech Communication Association Lyon, France August 25-29, 2013

A Computational Model of Perceptuo-Motor Processing in Speech Perception: Learning to Imitate and Categorize Synthetic CV Syllables

Raphaël Laurent (1), Jean-Luc Schwartz (2), Pierre Bessière (3), Julien Diard (4)

(1) LIG (UMR 5217), France
(2) GIPSA, France
(3) LPPA, France
(4) LPN (UMR 5105), France

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 perceptuomotor information. An imitation algorithm enables to learn the articulatory-to-acoustic mapping and the link between syllables and corresponding articulatory gestures, from acoustic inputs only: synthetic CV syllables generated with a human vocal tract model. We compare purely auditory, purely motor and perceptuo-motor syllable categorization under various noise levels.

Full Paper

Bibliographic reference.  Laurent, Raphaël / Schwartz, Jean-Luc / Bessière, Pierre / Diard, Julien (2013): "A computational model of perceptuo-motor processing in speech perception: learning to imitate and categorize synthetic CV syllables", In INTERSPEECH-2013, 2797-2801.