Exploration strategies for articulatory synthesis of complex syllable onsets

TL;DR

This paper presents an optimization-based framework for articulatory speech synthesis that automates the mapping from linguistic features to gestures, enabling the synthesis of complex syllable onsets with improved coarticulation quality.

Contribution

It introduces a novel optimization approach to learn articulatory mappings without manual effort, advancing high-quality speech synthesis of complex syllables.

Findings

Successful synthesis of complex syllable onsets

Effective modeling of coarticulation effects

Framework reduces manual intervention in mapping creation

Abstract

High-quality articulatory speech synthesis has many potential applications in speech science and technology. However, developing appropriate mappings from linguistic specification to articulatory gestures is difficult and time consuming. In this paper we construct an optimisation-based framework as a first step towards learning these mappings without manual intervention. We demonstrate the production of syllables with complex onsets and discuss the quality of the articulatory gestures with reference to coarticulation.