ed-cec: improving rare word recognition using asr postprocessing based on error detection and context-aware error correction

TL;DR

This paper introduces ed-cec, a postprocessing technique for ASR systems that detects errors and uses context-aware correction to improve rare word recognition, reducing word error rates across multiple datasets.

Contribution

The paper presents a novel error detection and context-aware correction method specifically designed for improving rare word recognition in ASR systems.

Findings

Significantly lower word error rates on five datasets.

Maintains reasonable inference speed.

Robust across different ASR systems.

Abstract

Automatic speech recognition (ASR) systems often encounter difficulties in accurately recognizing rare words, leading to errors that can have a negative impact on downstream tasks such as keyword spotting, intent detection, and text summarization. To address this challenge, we present a novel ASR postprocessing method that focuses on improving the recognition of rare words through error detection and context-aware error correction. Our method optimizes the decoding process by targeting only the predicted error positions, minimizing unnecessary computations. Moreover, we leverage a rare word list to provide additional contextual knowledge, enabling the model to better correct rare words. Experimental results across five datasets demonstrate that our proposed method achieves significantly lower word error rates (WERs) than previous approaches while maintaining a reasonable inference speed. Furthermore, our approach exhibits promising robustness across different ASR systems.