Calibrate and Refine! A Novel and Agile Framework for ASR-error Robust Intent Detection

TL;DR

This paper introduces CR-ID, a flexible framework with plug-and-play modules that enhances intent detection robustness against ASR errors without altering existing models, demonstrated by superior results on the SNIPS dataset.

Contribution

The paper presents a novel, model-agnostic framework with two modules that improve ASR-error robustness in intent detection, emphasizing versatility and ease of integration.

Findings

CR-ID outperforms baseline methods on SNIPS dataset

The framework effectively mitigates semantic drift caused by ASR errors

Modules are compatible with various existing intent detection models

Abstract

The past ten years have witnessed the rapid development of text-based intent detection, whose benchmark performances have already been taken to a remarkable level by deep learning techniques. However, automatic speech recognition (ASR) errors are inevitable in real-world applications due to the environment noise, unique speech patterns and etc, leading to sharp performance drop in state-of-the-art text-based intent detection models. Essentially, this phenomenon is caused by the semantic drift brought by ASR errors and most existing works tend to focus on designing new model structures to reduce its impact, which is at the expense of versatility and flexibility. Different from previous one-piece model, in this paper, we propose a novel and agile framework called CR-ID for ASR error robust intent detection with two plug-and-play modules, namely semantic drift calibration module (SDCM) and phonemic refinement module (PRM), which are both model-agnostic and thus could be easily integrated to any existing intent detection models without modifying their structures. Experimental results on SNIPS dataset show that, our proposed CR-ID framework achieves competitive performance and outperform all the baseline methods on ASR outputs, which verifies that CR-ID can effectively alleviate the semantic drift caused by ASR errors.