ISCA Archive Interspeech 2013
ISCA Archive Interspeech 2013

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

Raphaël Laurent, Jean-Luc Schwartz, Pierre Bessière, Julien Diard

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.


doi: 10.21437/Interspeech.2013-640

Cite as: Laurent, R., Schwartz, J.-L., Bessière, P., Diard, J. (2013) A computational model of perceptuo-motor processing in speech perception: learning to imitate and categorize synthetic CV syllables. Proc. Interspeech 2013, 2797-2801, doi: 10.21437/Interspeech.2013-640

@inproceedings{laurent13_interspeech,
  author={Raphaël Laurent and Jean-Luc Schwartz and Pierre Bessière and Julien Diard},
  title={{A computational model of perceptuo-motor processing in speech perception: learning to imitate and categorize synthetic CV syllables}},
  year=2013,
  booktitle={Proc. Interspeech 2013},
  pages={2797--2801},
  doi={10.21437/Interspeech.2013-640}
}