Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech
This addresses the problem of noisy speech recognition in radio communications for users in communication systems, with incremental improvements over existing methods.
The paper tackles robust end-to-end automatic speech recognition for radio communication by proposing a multitask-based joint training method that integrates speech enhancement and ASR without separate pre-training, achieving a relative WER reduction of 4.6% with joint training and up to 11.2% with data augmentation on the RATS dataset.
To realize robust end-to-end Automatic Speech Recognition(E2E ASR) under radio communication condition, we propose a multitask-based method to joint train a Speech Enhancement (SE) module as the front-end and an E2E ASR model as the back-end in this paper. One of the advantage of the proposed method is that the entire system can be trained from scratch. Different from prior works, either component here doesn't need to perform pre-training and fine-tuning processes separately. Through analysis, we found that the success of the proposed method lies in the following aspects. Firstly, multitask learning is essential, that is the SE network is not only learning to produce more Intelligent speech, it is also aimed to generate speech that is beneficial to recognition. Secondly, we also found speech phase preserved from noisy speech is critical for improving ASR performance. Thirdly, we propose a dual channel data augmentation training method to obtain further improvement.Specifically, we combine the clean and enhanced speech to train the whole system. We evaluate the proposed method on the RATS English data set, achieving a relative WER reduction of 4.6% with the joint training method, and up to a relative WER reduction of 11.2% with the proposed data augmentation method.