Minimum Word Error Training For Non-Autoregressive Transformer-Based Code-Switching ASR
Yizhou Peng, Jicheng Zhang, Haihua Xu, Hao Huang, Eng Siong Chng
Abstract
Non-autoregressive end-to-end ASR framework might be potentially appropriate for code-switching recognition task thanks to its inherent property that present output token being independent of historical ones. However, it still under-performs the state-of-the-art autoregressive ASR frameworks. In this paper, we propose various approaches to boosting the performance of a CTC-mask-based non-autoregressive Transformer under code-switching ASR scenario. To begin with, we attempt diversified masking method that are closely related with code-switching point, yielding an improved baseline model. More importantly, we employ Minimum Word Error (MWE) criterion to train the model. One of the challenges is how to generate a diversified hypothetical space, so as to obtain the average loss for a given ground truth. To address such a challenge, we explore different approaches to yielding desired N-best-based hypothetical space. We demonstrate the efficacy of the proposed methods on SEAME corpus, a challenging English-Mandarin code-switching corpus for Southeast Asia community. Compared with the cross-entropy-trained strong baseline, the proposed MWE training method achieves consistent performance improvement on the test sets.
BibTeX
@inproceedings{icassp2022_minimumworderror,
title = {Minimum Word Error Training For Non-Autoregressive Transformer-Based Code-Switching ASR},
author = {Yizhou Peng and Jicheng Zhang and Haihua Xu and Hao Huang and Eng Siong Chng},
booktitle = {ICASSP 2022},
year = {2022}
}