Unified speech and gesture synthesis using flow matching

TL;DR

This paper introduces a unified, efficient model for simultaneous speech and gesture synthesis from text, improving naturalness and coherence over previous methods.

Contribution

It presents a novel, simpler architecture trained with optimal-transport flow matching, enabling joint speech and gesture generation with higher quality and fewer network evaluations.

Findings

Enhanced speech naturalness and gesture human-likeness

Better cross-modal appropriateness in synthesis

Reduced computational steps for training

Abstract

As text-to-speech technologies achieve remarkable naturalness in read-aloud tasks, there is growing interest in multimodal synthesis of verbal and non-verbal communicative behaviour, such as spontaneous speech and associated body gestures. This paper presents a novel, unified architecture for jointly synthesising speech acoustics and skeleton-based 3D gesture motion from text, trained using optimal-transport conditional flow matching (OT-CFM). The proposed architecture is simpler than the previous state of the art, has a smaller memory footprint, and can capture the joint distribution of speech and gestures, generating both modalities together in one single process. The new training regime, meanwhile, enables better synthesis quality in much fewer steps (network evaluations) than before. Uni- and multimodal subjective tests demonstrate improved speech naturalness, gesture human-likeness, and cross-modal appropriateness compared to existing benchmarks. Please see https://shivammehta25.github.io/Match-TTSG/ for video examples and code.