Unified Speech And Gesture Synthesis Using Flow Matching

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.g

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keymehta2023unified

Related papers

• Fake It To Make It: Using Synthetic Data To Remedy The Data Shortage In Joint Multimodal Speech-and-gesture Synthesis (2024)6.34
• Vssflow: Unifying Video-conditioned Sound And Speech Generation Via Joint Learning (2025)0.00
• Gelina: Unified Speech And Gesture Synthesis Via Interleaved Token Prediction (2026)0.00
• Voiceflow: Efficient Text-to-speech With Rectified Flow Matching (2023)0.00
• A Conversational Gesture Synthesis System Based On Emotions And Semantics (2025)0.00
• Generative Pre-training For Speech With Flow Matching (2023)0.00
• Dim-gesture: Co-speech Gesture Generation With Adaptive Layer Normalization Mamba-2 Framework (2024)2.26
• Unisyn: An End-to-end Unified Model For Text-to-speech And Singing Voice Synthesis (2022)0.00