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.
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.