Training an articulatory synthesizer with continuous acoustic data

Conference proceedings article

Authors/Editors

Strategic Research Themes

No matching items found.

Publication Details

Author list: Prom-On S., Birkholz P., Xu Y.

Publisher: International Speech and Communication Association

Publication year: 2013

Start page: 349

End page: 353

Number of pages: 5

ISSN: 2308-457X

eISSN: 2308-457X

URL: https://www.scopus.com/inward/record.uri?eid=2-s2.0-84901774110&partnerID=40&md5=4f80a68edcbe1c5ede19b200baaa1443

Languages: English-Great Britain (EN-GB)

Abstract

This paper reports preliminary results of our effort to address the acoustic-to-articulatory inversion problem. We tested an approach that simulates speech production acquisition as a distal learning task, with acoustic signals of natural utterances in the form of MFCC as input, VocalTractLab - A 3D articulatory synthesizer controlled by target approximation models as the learner, and stochastic gradient descent as the training method. The approach was tested on a number of natural utterances, and the results were highly encouraging. Copyright ฉ 2013 ISCA.

Keywords

Acoustic-to-articulatory inversion, Articulatory synthesis, Embodiment constraint, Target approximation