Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition
Xichen Pan, Peiyu Chen, Yichen Gong, Helong Zhou, Xinbing Wang, Zhouhan Lin
Abstract
Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to make use of unlabelled unimodal data. On the other side, although the effectiveness of large-scale self-supervised learning is well established in both audio and visual modalities, how to integrate those pre-trained models into a multimodal scenario remains underexplored. In this work, we successfully leverage unimodal self-supervised learning to promote the multimodal AVSR. In particular, audio and visual front-ends are trained on large-scale unimodal datasets, then we integrate components of both front-ends into a larger multimodal framework which learns to recognize parallel audio-visual data into characters through a combination of CTC and seq2seq decoding. We show that both components inherited from unimodal self-supervised learning cooperate well, resulting in that the multimodal framework yields competitive results through fine-tuning. Our model is experimentally validated on both word-level and sentence-level tasks. Especially, even without an external language model, our proposed model raises the state-of-the-art performances on the widely accepted Lip Reading Sentences 2 (LRS2) dataset by a large margin, with a relative improvement of 30%.- Anthology ID:
- 2022.acl-long.308
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Smaranda Muresan, Preslav Nakov, Aline Villavicencio
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4491–4503
- Language:
- URL:
- https://aclanthology.org/2022.acl-long.308
- DOI:
- 10.18653/v1/2022.acl-long.308
- Cite (ACL):
- Xichen Pan, Peiyu Chen, Yichen Gong, Helong Zhou, Xinbing Wang, and Zhouhan Lin. 2022. Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4491–4503, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition (Pan et al., ACL 2022)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2022.acl-long.308.pdf
- Code
- lumia-group/leveraging-self-supervised-learning-for-avsr
- Data
- ImageNet, LRS2, LRW, Libri-Light, LibriSpeech