Low-resource speech recognition has been long-suffering from insufficient training data. In this paper, we propose an approach that leverages neighboring languages to improve low-resource scenario performance, founded on the hypothesis that similar linguistic units in neighboring languages exhibit comparable term frequency distributions, which enables us to construct a Huffman tree for performing multilingual hierarchical Softmax decoding. This hierarchical structure enables cross-lingual knowledge sharing among similar tokens, thereby enhancing low-resource training outcomes. Empirical analyses demonstrate that our method is effective in improving the accuracy and efficiency of low-resource speech recognition.
@article{arxiv.2204.03855,
title = {Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognition},
author = {Qianying Liu and Zhuo Gong and Zhengdong Yang and Yuhang Yang and Sheng Li and Chenchen Ding and Nobuaki Minematsu and Hao Huang and Fei Cheng and Chenhui Chu and Sadao Kurohashi},
journal= {arXiv preprint arXiv:2204.03855},
year = {2023}
}