Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding
This addresses the problem of noise propagation in SLU systems for real-world applications, but it is incremental as it builds on existing domain adaptation techniques.
The paper tackles the performance degradation of spoken language understanding systems due to noise from upstream components like ASR errors, by proposing a domain adaptation method that embeds high- and low-quality samples into similar vector spaces and uses a denoising generation model. Experiments on Snips and a large in-house dataset show it outperforms baselines on noisy data and enhances robustness.
Spoken language understanding (SLU) system usually consists of various pipeline components, where each component heavily relies on the results of its upstream ones. For example, Intent detection (ID), and slot filling (SF) require its upstream automatic speech recognition (ASR) to transform the voice into text. In this case, the upstream perturbations, e.g. ASR errors, environmental noise and careless user speaking, will propagate to the ID and SF models, thus deteriorating the system performance. Therefore, the well-performing SF and ID models are expected to be noise resistant to some extent. However, existing models are trained on clean data, which causes a \textit{gap between clean data training and real-world inference.} To bridge the gap, we propose a method from the perspective of domain adaptation, by which both high- and low-quality samples are embedding into similar vector space. Meanwhile, we design a denoising generation model to reduce the impact of the low-quality samples. Experiments on the widely-used dataset, i.e. Snips, and large scale in-house dataset (10 million training examples) demonstrate that this method not only outperforms the baseline models on real-world (noisy) corpus but also enhances the robustness, that is, it produces high-quality results under a noisy environment. The source code will be released.