Meta-Transfer Learning for Code-Switched Speech Recognition
Abstract
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- April 2020
- DOI:
- 10.48550/arXiv.2004.14228
- arXiv:
- arXiv:2004.14228
- Bibcode:
- 2020arXiv200414228I
- Keywords:
-
- Computer Science - Computation and Language;
- Computer Science - Sound;
- Electrical Engineering and Systems Science - Audio and Speech Processing
- E-Print:
- Accepted in ACL 2020. The first two authors contributed equally to this work