TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis
Abstract
This paper introduces Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning (TARO), a novel framework for high-fidelity and temporally coherent video-to-audio synthesis. Built upon flow-based transformers, which offer stable training and continuous transformations for enhanced synchronization and audio quality, TARO introduces two key innovations: (1) Timestep-Adaptive Representation Alignment (TRA), which dynamically aligns latent representations by adjusting alignment strength based on the noise schedule, ensuring smooth evolution and improved fidelity, and (2) Onset-Aware Conditioning (OAC), which integrates onset cues that serve as sharp event-driven markers of audio-relevant visual moments to enhance synchronization with dynamic visual events. Extensive experiments on the VGGSound and Landscape datasets demonstrate that TARO outperforms prior methods, achieving relatively 53% lower Frechet Distance (FD), 29% lower Frechet Audio Distance (FAD), and a 97.19% Alignment Accuracy, highlighting its superior audio quality and synchronization precision.
Keywords
Cite
@article{arxiv.2504.05684,
title = {TARO: Timestep-Adaptive Representation Alignment with Onset-Aware Conditioning for Synchronized Video-to-Audio Synthesis},
author = {Tri Ton and Ji Woo Hong and Chang D. Yoo},
journal= {arXiv preprint arXiv:2504.05684},
year = {2025}
}
Comments
Accepted to ICCV 2025. Please visit our project page at https://triton99.github.io/taro-site/