The reviewed record of science sign in
Pith

arxiv: 2006.00782 · v1 · pith:5DEYT3VL · submitted 2020-06-01 · eess.AS · cs.CL· cs.SD

Learning to Recognize Code-switched Speech Without Forgetting Monolingual Speech Recognition

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:5DEYT3VLrecord.jsonopen to challenge →

classification eess.AS cs.CLcs.SD
keywords monolingualspeechcode-switchedmodelsdatafine-tuningwithoutaccess
0
0 comments X
read the original abstract

Recently, there has been significant progress made in Automatic Speech Recognition (ASR) of code-switched speech, leading to gains in accuracy on code-switched datasets in many language pairs. Code-switched speech co-occurs with monolingual speech in one or both languages being mixed. In this work, we show that fine-tuning ASR models on code-switched speech harms performance on monolingual speech. We point out the need to optimize models for code-switching while also ensuring that monolingual performance is not sacrificed. Monolingual models may be trained on thousands of hours of speech which may not be available for re-training a new model. We propose using the Learning Without Forgetting (LWF) framework for code-switched ASR when we only have access to a monolingual model and do not have the data it was trained on. We show that it is possible to train models using this framework that perform well on both code-switched and monolingual test sets. In cases where we have access to monolingual training data as well, we propose regularization strategies for fine-tuning models for code-switching without sacrificing monolingual accuracy. We report improvements in Word Error Rate (WER) in monolingual and code-switched test sets compared to baselines that use pooled data and simple fine-tuning.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.