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 propose a new learning method, meta-transfer learning, to transfer learn on a system in a low-resource setting by judiciously extracting information from high-resource monolingual datasets . Based on experimental results, our model outperforms existing baselines on speech recognition and language modeling tasks, and is faster to converge .

Links: PDF - Abstract

Code :

None

Keywords : language - transfer - learning - recognition - speech -

Leave a Reply

Your email address will not be published. Required fields are marked *