Evoc-Learn - High quality simulation of early vocal learning

Conference proceedings article

Authors/Editors

Strategic Research Themes

Publication Details

Author list: Xu, Yia; Xu, Anqi; van Niekerk, Daniel R.; Gerazov, Branislav; Birkholz, Peter; Krug, Paul Konstantin; Prom-On, Santitham; Halliday, Lorna F.;

Publisher: International Speech Communication Association

Publication year: 2022

Volume number: 2022-September

Start page: 3665

End page: 3666

Number of pages: 2

ISSN: 2308-457X

URL: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85140065822&partnerID=40&md5=69ea04d1743387611697a3cd1c3b7220

Languages: English-Great Britain (EN-GB)

Abstract

Evoc-Learn is a system for simulating early vocal learning of spoken language in ways that can overcome some of the major bottlenecks in vocal learning. The system consists of VocalTractLab, a geometrical three-dimensional vocal tract model for simulating aeroacoustics and articulatory dynamics, a coarticulation model for controlling the temporal dynamics of articulation, and a sensory feedback system for guiding the learning process. We will demonstrate each component of Evoc-Learn and show how they work together to simulate the learning of highly intelligible speech. Copyright © 2022 ISCA.

Keywords

CV coarticulation, sensory feedback, speech perception