An Approach to Improve Robustness of NLP Systems against ASR Errors
This work addresses robustness for speech-enabled NLP systems, but it is incremental as it builds on existing data augmentation methods.
The paper tackles the problem of ASR errors degrading NLP system performance by generating ASR-plausible noise using pre-trained language models for data augmentation, achieving state-of-the-art results on spoken language translation and understanding tasks.
Speech-enabled systems typically first convert audio to text through an automatic speech recognition (ASR) model and then feed the text to downstream natural language processing (NLP) modules. The errors of the ASR system can seriously downgrade the performance of the NLP modules. Therefore, it is essential to make them robust to the ASR errors. Previous work has shown it is effective to employ data augmentation methods to solve this problem by injecting ASR noise during the training process. In this paper, we utilize the prevalent pre-trained language model to generate training samples with ASR-plausible noise. Compare to the previous methods, our approach generates ASR noise that better fits the real-world error distribution. Experimental results on spoken language translation(SLT) and spoken language understanding (SLU) show that our approach effectively improves the system robustness against the ASR errors and achieves state-of-the-art results on both tasks.