Boosting Chinese ASR Error Correction with Dynamic Error Scaling Mechanism

TL;DR

This paper proposes a dynamic error scaling mechanism for Chinese ASR error correction, effectively integrating word-level and phonetic features to improve correction accuracy in the context of Chinese language complexities.

Contribution

It introduces a novel dynamic error scaling approach that enhances phonetic and semantic feature fusion for Chinese ASR error correction, addressing limitations of existing models.

Findings

Significant improvement in correction accuracy on benchmark datasets

Effective fusion of word-level and phonetic features

Robust handling of character-based errors

Abstract

Chinese Automatic Speech Recognition (ASR) error correction presents significant challenges due to the Chinese language's unique features, including a large character set and borderless, morpheme-based structure. Current mainstream models often struggle with effectively utilizing word-level features and phonetic information. This paper introduces a novel approach that incorporates a dynamic error scaling mechanism to detect and correct phonetically erroneous text generated by ASR output. This mechanism operates by dynamically fusing word-level features and phonetic information, thereby enriching the model with additional semantic data. Furthermore, our method implements unique error reduction and amplification strategies to address the issues of matching wrong words caused by incorrect characters. Experimental results indicate substantial improvements in ASR error correction, demonstrating the effectiveness of our proposed method and yielding promising results on established datasets.