Méthodologie 3-way d'extraction d'un modèle articulatoire de la parole à partir des données d'un locuteur

Martine Cadot 1 Yves Laprie 2
1 ABC - Machine Learning and Computational Biology
LORIA - ALGO - Department of Algorithms, Computation, Image and Geometry
2 PAROLE - Analysis, perception and recognition of speech
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : For speaking, a speaker sets in motion a complex set of articulators: the jaw that opens more or less, the tongue which takes many shapes and positions, the lips that allow him to leave the air escaping more or less abruptly, etc.. The best-known articulary model is the one of Maeda (1990), derived from Principal Component Analysis made on arrays of coordinates of points of the articulators of a speaker talking. We propose a 3-way analysis of the same data type, after converting tables into distances. We validate our model by predicting spoken sounds, which prediction proved almost as good as the acoustic model, and even better when co-articulation is taken into account.
Liste complète des métadonnées

Cited literature [10 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00934436
Contributor : Martine Cadot <>
Submitted on : Thursday, February 6, 2014 - 7:00:05 AM
Last modification on : Tuesday, December 18, 2018 - 4:38:02 PM
Document(s) archivé(s) le : Tuesday, May 6, 2014 - 10:06:20 PM

File

cadot_laprie_afdcegc2014_V9.pd...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00934436, version 1

Citation

Martine Cadot, Yves Laprie. Méthodologie 3-way d'extraction d'un modèle articulatoire de la parole à partir des données d'un locuteur. Atelier Fouille de Données Complexes des 14èmes Journées Francophones "Extraction et Gestion des Connaissances", Jan 2014, Rennes, France. pp.1-12. ⟨hal-00934436⟩

Share

Metrics

Record views

700

Files downloads

288