Improving Noisy Student Training on Non-target Domain Data for Automatic Speech Recognition
share
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 performances of NST on non-target domain data in ASR tasks. Hypothesis with and without Language Model are generated and CER differences between them are utilized as a filter threshold. Results reveal that significant improvements of 10.4 no data filtering baselines. We can achieve 3.31 which is best result from our knowledge without any other supervised data. We also perform evaluations on supervised 1000 hour AISHELL-2 dataset and competitive results of 4.72
READ FULL TEXT