VSSFlow: Unifying Video-conditioned Sound and Speech Generation via Joint Learning
By: Xin Cheng , Yuyue Wang , Xihua Wang and more
Potential Business Impact:
Makes videos talk and make sounds.
Video-conditioned sound and speech generation, encompassing video-to-sound (V2S) and visual text-to-speech (VisualTTS) tasks, are conventionally addressed as separate tasks, with limited exploration to unify them within a signle framework. Recent attempts to unify V2S and VisualTTS face challenges in handling distinct condition types (e.g., heterogeneous video and transcript conditions) and require complex training stages. Unifying these two tasks remains an open problem. To bridge this gap, we present VSSFlow, which seamlessly integrates both V2S and VisualTTS tasks into a unified flow-matching framework. VSSFlow uses a novel condition aggregation mechanism to handle distinct input signals. We find that cross-attention and self-attention layer exhibit different inductive biases in the process of introducing condition. Therefore, VSSFlow leverages these inductive biases to effectively handle different representations: cross-attention for ambiguous video conditions and self-attention for more deterministic speech transcripts. Furthermore, contrary to the prevailing belief that joint training on the two tasks requires complex training strategies and may degrade performance, we find that VSSFlow benefits from the end-to-end joint learning process for sound and speech generation without extra designs on training stages. Detailed analysis attributes it to the learned general audio prior shared between tasks, which accelerates convergence, enhances conditional generation, and stabilizes the classifier-free guidance process. Extensive experiments demonstrate that VSSFlow surpasses the state-of-the-art domain-specific baselines on both V2S and VisualTTS benchmarks, underscoring the critical potential of unified generative models.
Similar Papers
Taming Text-to-Sounding Video Generation via Advanced Modality Condition and Interaction
CV and Pattern Recognition
Makes videos match sounds and words perfectly.
Hear What Matters! Text-conditioned Selective Video-to-Audio Generation
CV and Pattern Recognition
Makes videos play only the sound you want.
MeanFlow-Accelerated Multimodal Video-to-Audio Synthesis via One-Step Generation
Sound
Makes silent videos talk in one step.