Internet Archive Scholar

End-to-End Code Switching Language Models for Automatic Speech Recognition [article]

Ahan M. R., Shreyas Sunil Kulkarni
2020 arXiv   pre-print

Preserved Fulltext

Web Archive Capture PDF (344.4 kB)
https://web.archive.org/web/20200623073422/https://arxiv.org/pdf/2006.08870v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL. The file type is application/pdf.

In this paper, we particularly work on the code-switched text, one of the most common occurrences in the bilingual communities across the world. Due to the discrepancies in the extraction of code-switched text from an Automated Speech Recognition(ASR) module, and thereby extracting the monolingual text from the code-switched text, we propose an approach for extracting monolingual text using Deep Bi-directional Language Models(LM) such as BERT and other Machine Translation models, and also
more » ... e different ways of extracting code-switched text from the ASR model. We also explain the robustness of the model by comparing the results of Perplexity and other different metrics like WER, to the standard bi-lingual text output without any external information.
arXiv:2006.08870v1 fatcat:lz6q5ke3rjehzexj4aj7izmr5y
Citation

Ahan M. R., Shreyas Sunil Kulkarni. "End-to-End Code Switching Language Models for Automatic Speech Recognition." arXiv (2020)