V2sflow: Video-to-speech Generation With Speech Decomposition And Rectified Flow

Abstract

In this paper, we introduce V2SFlow, a novel Video-to-Speech (V2S) framework designed to generate natural and intelligible speech directly from silent talking face videos. While recent V2S systems have shown promising results on constrained datasets with limited speakers and vocabularies, their performance often degrades on real-world, unconstrained datasets due to the inherent variability and complexity of speech signals. To address these challenges, we decompose the speech signal into manageable subspaces (content, pitch, and speaker information), each representing distinct speech attributes, and predict them directly from the visual input. To generate coherent and realistic speech from these predicted attributes, we employ a rectified flow matching decoder built on a Transformer architecture, which models efficient probabilistic pathways from random noise to the target speech distribution. Extensive experiments demonstrate that V2SFlow significantly outperforms state-of-the-art meth

Stats

• citations5
• S2 citations—
• github stars21
• HF likes0
• heat score8.52
• arxiv keychoi2024v2sflow

Related papers

• Vssflow: Unifying Video-conditioned Sound And Speech Generation Via Joint Learning (2025)0.00
• Voiceflow: Efficient Text-to-speech With Rectified Flow Matching (2023)0.00
• Flowvocoder: A Small Footprint Neural Vocoder Based Normalizing Flow For Speech Synthesis (2021)0.00
• Diflow-tts: Compact And Low-latency Zero-shot Text-to-speech With Factorized Discrete Flow Matching (2025)0.00
• Frieren: Efficient Video-to-audio Generation Network With Rectified Flow Matching (2024)0.00
• Flow-tsvad: Target-speaker Voice Activity Detection Via Latent Flow Matching (2024)0.00
• Voicerestore: Flow-matching Transformers For Speech Recording Quality Restoration (2025)0.00
• Generative Pre-training For Speech With Flow Matching (2023)0.00