Noisy Student Training (NST) has recently demonstrated extremely strong performance in Automatic Speech Recognition(ASR). In this paper, we propose a data selection strategy named LM Filter to improve the performance of NST on non-target domain data in ASR tasks. Hypotheses with and without a Language Model are generated and the CER differences between them are utilized as a filter threshold. Results reveal that significant improvements of 10.4% compared with no data filtering baselines. We can achieve 3.31% CER in AISHELL-1 test set, which is best result from our knowledge without any other supervised data. We also perform evaluations on the supervised 1000 hour AISHELL-2 dataset and competitive results of 4.73% CER can be achieved.
@article{arxiv.2211.04717,
title = {Improving Noisy Student Training on Non-target Domain Data for Automatic Speech Recognition},
author = {Yu Chen and Wen Ding and Junjie Lai},
journal= {arXiv preprint arXiv:2211.04717},
year = {2023}
}
Comments
This paper is accepted by the ICASSP 2023 conference