Low-resource speech recognition has been long-suffering from insufficient training data. In this paper, we propose an approach that allows neighboring languages to help improve low-resource scenario performance. We assume similar units in neighbor languages share similar term frequency and form a Huffman tree to perform multilingual hierarchical Softmax decoding. The hierarchical structure can allow similar tokens to share knowledge across languages, thus benefiting low-resource training. Experimental results show that our method can improve the accuracy and efficiency of low-resource speech recognition.
音声認識
氏名 | コース | 研究室 | 役職/学年 |
---|---|---|---|
Zhengdong Yang | 知能情報学コース | 言語メディア研究室 | 博士1回生 |