English

Audio-Visual Speech Enhancement and Separation by Utilizing Multi-Modal Self-Supervised Embeddings

Audio and Speech Processing 2023-06-02 v3 Sound

Abstract

AV-HuBERT, a multi-modal self-supervised learning model, has been shown to be effective for categorical problems such as automatic speech recognition and lip-reading. This suggests that useful audio-visual speech representations can be obtained via utilizing multi-modal self-supervised embeddings. Nevertheless, it is unclear if such representations can be generalized to solve real-world multi-modal AV regression tasks, such as audio-visual speech enhancement (AVSE) and audio-visual speech separation (AVSS). In this study, we leveraged the pre-trained AV-HuBERT model followed by an SE module for AVSE and AVSS. Comparative experimental results demonstrate that our proposed model performs better than the state-of-the-art AVSE and traditional audio-only SE models. In summary, our results confirm the effectiveness of our proposed model for the AVSS task with proper fine-tuning strategies, demonstrating that multi-modal self-supervised embeddings obtained from AV-HuBERT can be generalized to audio-visual regression tasks.

Keywords

Cite

@article{arxiv.2210.17456,
  title  = {Audio-Visual Speech Enhancement and Separation by Utilizing Multi-Modal Self-Supervised Embeddings},
  author = {I-Chun Chern and Kuo-Hsuan Hung and Yi-Ting Chen and Tassadaq Hussain and Mandar Gogate and Amir Hussain and Yu Tsao and Jen-Cheng Hou},
  journal= {arXiv preprint arXiv:2210.17456},
  year   = {2023}
}

Comments

ICASSP AMHAT 2023

R2 v1 2026-06-28T04:51:56.636Z