GTR-Voice: Articulatory Phonetics Informed Controllable Expressive Speech Synthesis

TL;DR

This paper introduces GTR-Voice, a new articulatory phonetics-based framework for controllable expressive speech synthesis, enabling nuanced manipulation of voice features like glottalization, tenseness, and resonance.

Contribution

It proposes a novel GTR framework for expressive speech synthesis, creates a high-quality dataset with GTR annotations, and demonstrates precise controllability in TTS models.

Findings

GTR framework effectively guides expressive speech synthesis.

High classification accuracy of GTR annotations.

Models achieve fine-grained control over voice features.

Abstract

Expressive speech synthesis aims to generate speech that captures a wide range of para-linguistic features, including emotion and articulation, though current research primarily emphasizes emotional aspects over the nuanced articulatory features mastered by professional voice actors. Inspired by this, we explore expressive speech synthesis through the lens of articulatory phonetics. Specifically, we define a framework with three dimensions: Glottalization, Tenseness, and Resonance (GTR), to guide the synthesis at the voice production level. With this framework, we record a high-quality speech dataset named GTR-Voice, featuring 20 Chinese sentences articulated by a professional voice actor across 125 distinct GTR combinations. We verify the framework and GTR annotations through automatic classification and listening tests, and demonstrate precise controllability along the GTR dimensions on two fine-tuned expressive TTS models. We open-source the dataset and TTS models.