Meta-Adapter: Efficient Cross-Lingual Adaptation With Meta-Learning
Wenxin Hou, Yidong Wang, Shengzhou Gao, Takahiro Shinozaki
-
SPS
IEEE Members: $11.00
Non-members: $15.00Length: 00:09:11
Transfer learning from a multilingual model has shown favorable results on low-resource automatic speech recognition (ASR). However, full-model fine-tuning generates a separate model for every target language and is not suitable for deploying and maintaining in production. The key challenge lies in how to efficiently extend the pre-trained model with fewer parameters. In this paper, we propose to combine the adapter module with meta-learning algorithms to achieve high recognition performance under low-resource settings and improve the parameter-efficiency of the model. Extensive experiments show that our methods can achieve comparable or even superior recognition rates than the state-of-the-art baselines on low-resource languages, especially under very-low-resource conditions, with a significantly smaller model profile.
Chairs:
Shinji Watanabe