An increasing number of people in the world today speak a mixed-language as a result of being multilingual. However, building a speech recognition system for code-switching remains difficult due to the availability of limited resources and the expense and significant effort required to collect mixed-language data. We therefore propose a new learning method, meta-transfer learning, to transfer learn on a code-switched speech recognition system in a low-resource setting by judiciously extracting information from high-resource monolingual datasets. Our model learns to recognize individual languages, and transfer them so as to better recognize mixed-language speech by conditioning the optimization on the code-switching data. Based on experimental results, our model outperforms existing baselines on speech recognition and language modeling tasks, and is faster to converge.
@article{arxiv.2004.14228,
title = {Meta-Transfer Learning for Code-Switched Speech Recognition},
author = {Genta Indra Winata and Samuel Cahyawijaya and Zhaojiang Lin and Zihan Liu and Peng Xu and Pascale Fung},
journal= {arXiv preprint arXiv:2004.14228},
year = {2020}
}
Comments
Accepted in ACL 2020. The first two authors contributed equally to this work