The attention-based deep contextual biasing method has been demonstrated to effectively improve the recognition performance of end-to-end automatic speech recognition (ASR) systems on given contextual phrases. However, unlike shallow fusion methods that directly bias the posterior of the ASR model, deep biasing methods implicitly integrate contextual information, making it challenging to control the degree of bias. In this study, we introduce a spike-triggered deep biasing method that simultaneously supports both explicit and implicit bias. Moreover, both bias approaches exhibit significant improvements and can be cascaded with shallow fusion methods for better results. Furthermore, we propose a context sampling enhancement strategy and improve the contextual phrase filtering algorithm. Experiments on the public WenetSpeech Mandarin biased-word dataset show a 32.0% relative CER reduction compared to the baseline model, with an impressively 68.6% relative CER reduction on contextual phrases.
@article{arxiv.2310.04657,
title = {Spike-Triggered Contextual Biasing for End-to-End Mandarin Speech Recognition},
author = {Kaixun Huang and Ao Zhang and Binbin Zhang and Tianyi Xu and Xingchen Song and Lei Xie},
journal= {arXiv preprint arXiv:2310.04657},
year = {2023}
}