COSMO SylPhon: A Bayesian Perceptuo-motor Model to Assess Phonological Learning

Abstract : During speech development, babies learn to perceive and produce speech units, especially syllables and phonemes. However , the mechanisms underlying the acquisition of speech units still remain unclear. We propose a Bayesian model of speech communication, named "COSMO SylPhon", for studying the acquisition of both syllables and phonemes. In this model, speech development involves a sensory learning phase, mainly concerned with perception development, and a motor learning phase, mainly concerned with production development. We study how an agent can learn speech units during these two phases through an unsupervised learning process based on syllable stimuli. We show that the learning process enables to efficiently learn the distribution of syllabic stimuli provided in the environment. Importantly, we show that if agents are equipped with a bootstrap process inspired by the Frame-Content Theory of speech development, they learn to associate consonants to specific articulatory gestures, providing the basis for consonantal articulatory invariance.
Type de document :
Communication dans un congrès
19th Annual Conference of the International Speech Communication Association (Interspeech 2018), Sep 2018, Hyderabad, India. pp.3786-3790, 〈10.21437/interspeech.2018-73〉
Liste complète des métadonnées

Littérature citée [2 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-02002373
Contributeur : Julien Diard <>
Soumis le : jeudi 31 janvier 2019 - 16:12:51
Dernière modification le : vendredi 8 février 2019 - 01:19:48

Fichier

barnaud18b.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Citation

Marie-Lou Barnaud, Julien Diard, Pierre Bessière, Jean-Luc Schwartz. COSMO SylPhon: A Bayesian Perceptuo-motor Model to Assess Phonological Learning. 19th Annual Conference of the International Speech Communication Association (Interspeech 2018), Sep 2018, Hyderabad, India. pp.3786-3790, 〈10.21437/interspeech.2018-73〉. 〈hal-02002373〉

Partager

Métriques

Consultations de la notice

19

Téléchargements de fichiers

10