SALSA-V: Shortcut-Augmented Long-form Synchronized Audio from Videos

Amir Dellali, Luca A Lanzendörfer, Florian Grötschla, Roger Wattenhofer

Keywords: video-to-audio, audio generation, diffusion

Abstract: We propose SALSA-V, a multimodal video-to-audio generation model capable of synthesizing highly synchronized, high-fidelity long-form audio from silent video content. Our approach introduces a masked diffusion objective, enabling audio-conditioned generation and the seamless synthesis of audio sequences of unconstrained length. Additionally, by integrating a shortcut loss into our training process, we achieve rapid generation of high-quality audio samples in as few as eight sampling steps, paving the way for near-real-time applications without requiring dedicated fine-tuning or retraining. We demonstrate that SALSA-V significantly outperforms existing state-of-the-art methods in both audiovisual alignment and synchronization with video content in quantiative evaluation and a human listening study. Furthermore, our use of random masking during training enables our model to match spectral characteristics of reference audio samples, broadening its applicability to professional audio synthesis tasks such as Foley generation and sound design.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 11727