Assessing Idiosyncrasies in a Bayesian Model of Speech Communication

Marie-Lou Barnaud (1, 2) , Julien Diard (2) , Pierre Bessière (3, 4) , Jean-Luc Schwartz (1)

1 GIPSA-PCMD - GIPSA - Perception, Contrôle, Multimodalité et Dynamiques de la parole
2 LPNC - Laboratoire de Psychologie et NeuroCognition
3 ISIR - Institut des Systèmes Intelligents et de Robotique
4 AMAC

Although speakers of one specific language share the same phoneme representations, their productions can differ. We propose to investigate the development of these differences in production , called idiosyncrasies, by using a Bayesian model of communication. Supposing that idiosyncrasies appear during the development of the motor system, we present two versions of the motor learning phase, both based on the guidance of an agent master: " a repetition model " where agents try to imitate the sounds produced by the master and " a communication model " where agents try to replicate the phonemes produced by the master. Our experimental results show that only the " communication model " provides production idiosyncrasies, suggesting that idiosyncrasies are a natural output of a motor learning process based on a communicative goal.

Mots clés: speech development; idiosyncrasies; Bayesian modeling; motor learning

Domaines: Informatique; Linguistique

Marie-Lou Barnaud, Julien Diard, Pierre Bessière, Jean-Luc Schwartz. Assessing Idiosyncrasies in a Bayesian Model of Speech Communication. Interspeech 2016 - 17th Annual Conference of the International Speech Communication Association, Sep 2016, San Francisco, United States. ⟨10.21437/Interspeech.2016-396⟩. ⟨hal-01371722⟩