Large Language Model Should Understand Pinyin for Chinese ASR Error Correction
This addresses error correction in Chinese ASR systems, offering an incremental improvement for speech processing applications.
The paper tackled the problem of improving Chinese automatic speech recognition error correction by incorporating Pinyin phonetic representations, resulting in consistent performance gains over text-only methods on Aishell-1 and Common Voice datasets.
Large language models can enhance automatic speech recognition systems through generative error correction. In this paper, we propose Pinyin-enhanced GEC, which leverages Pinyi, the phonetic representation of Mandarin Chinese, as supplementary information to improve Chinese ASR error correction. Our approach only utilizes synthetic errors for training and employs the one-best hypothesis during inference. Additionally, we introduce a multitask training approach involving conversion tasks between Pinyin and text to align their feature spaces. Experiments on the Aishell-1 and the Common Voice datasets demonstrate that our approach consistently outperforms GEC with text-only input. More importantly, we provide intuitive explanations for the effectiveness of PY-GEC and multitask training from two aspects: 1) increased attention weight on Pinyin features; and 2) aligned feature space between Pinyin and text hidden states.