Interventional Speech Noise Injection for ASR Generalizable Spoken Language Understanding
This addresses the issue of SLU model degradation due to ASR inaccuracies, offering a more generalizable solution compared to prior biased methods, though it is incremental in improving noise injection techniques.
The paper tackles the problem of ASR errors degrading spoken language understanding (SLU) model performance by proposing a novel augmentation method that introduces ASR-plausible noises to train models for robustness, resulting in enhanced generalizability against unseen ASR systems.
Recently, pre-trained language models (PLMs) have been increasingly adopted in spoken language understanding (SLU). However, automatic speech recognition (ASR) systems frequently produce inaccurate transcriptions, leading to noisy inputs for SLU models, which can significantly degrade their performance. To address this, our objective is to train SLU models to withstand ASR errors by exposing them to noises commonly observed in ASR systems, referred to as ASR-plausible noises. Speech noise injection (SNI) methods have pursued this objective by introducing ASR-plausible noises, but we argue that these methods are inherently biased towards specific ASR systems, or ASR-specific noises. In this work, we propose a novel and less biased augmentation method of introducing the noises that are plausible to any ASR system, by cutting off the non-causal effect of noises. Experimental results and analyses demonstrate the effectiveness of our proposed methods in enhancing the robustness and generalizability of SLU models against unseen ASR systems by introducing more diverse and plausible ASR noises in advance.