CCStereo: Audio-Visual Contextual and Contrastive Learning for Binaural Audio Generation
Abstract
Binaural audio generation (BAG) aims to convert monaural audio to stereo audio using visual prompts, requiring a deep understanding of spatial and semantic information. However, current models risk overfitting to room environments and lose fine-grained spatial details. In this paper, we propose a new audio-visual binaural generation model incorporating an audio-visual conditional normalisation layer that dynamically aligns the mean and variance of the target difference audio features using visual context, along with a new contrastive learning method to enhance spatial sensitivity by mining negative samples from shuffled visual features. We also introduce a cost-efficient way to utilise test-time augmentation in video data to enhance performance. Our approach achieves state-of-the-art generation accuracy on the FAIR-Play and MUSIC-Stereo benchmarks.
Cite
@article{arxiv.2501.02786,
title = {CCStereo: Audio-Visual Contextual and Contrastive Learning for Binaural Audio Generation},
author = {Yuanhong Chen and Kazuki Shimada and Christian Simon and Yukara Ikemiya and Takashi Shibuya and Yuki Mitsufuji},
journal= {arXiv preprint arXiv:2501.02786},
year = {2025}
}