BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognition
Abstract
Mixture-of-experts based models, which use language experts to extract language-specific representations effectively, have been well applied in code-switching automatic speech recognition. However, there is still substantial space to improve as similar pronunciation across languages may result in ineffective multi-language modeling and inaccurate language boundary estimation. To eliminate these drawbacks, we propose a cross-layer language adapter and a boundary-aware training method, namely Boundary-Aware Mixture-of-Experts (BA-MoE). Specifically, we introduce language-specific adapters to separate language-specific representations and a unified gating layer to fuse representations within each encoder layer. Second, we compute language adaptation loss of the mean output of each language-specific adapter to improve the adapter module's language-specific representation learning. Besides, we utilize a boundary-aware predictor to learn boundary representations for dealing with language boundary confusion. Our approach achieves significant performance improvement, reducing the mixture error rate by 16.55\% compared to the baseline on the ASRU 2019 Mandarin-English code-switching challenge dataset.
Cite
@article{arxiv.2310.02629,
title = {BA-MoE: Boundary-Aware Mixture-of-Experts Adapter for Code-Switching Speech Recognition},
author = {Peikun Chen and Fan Yu and Yuhao Lian and Hongfei Xue and Xucheng Wan and Naijun Zheng and Huan Zhou and Lei Xie},
journal= {arXiv preprint arXiv:2310.02629},
year = {2023}
}
Comments
Accepted by ASRU2023