Zhaojiang Lin, Pascale Fung, Peng Xu, Samuel Cahyawijaya, Zihan Liu, Genta Indra Winata
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 codeswitching data. Based on experimental results, our model outperforms existing baselines on speech recognition and language modeling tasks, and is faster to converge.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2004.14228")
get_code_for_paper("2004.14228")
have("2004.14228")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2004.14228.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2004.14228)
Connect an agent — have() is free.