Chain of Correction for Full-text Speech Recognition with Large Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911474195103744 |
|---|---|
| author | Tang, Zhiyuan Wang, Dong Zhou, Zhikai Liu, Yong Huang, Shen Shang, Shidong |
| author_facet | Tang, Zhiyuan Wang, Dong Zhou, Zhikai Liu, Yong Huang, Shen Shang, Shidong |
| contents | Full-text error correction with Large Language Models (LLMs) for Automatic Speech Recognition (ASR) is attracting increased attention for its ability to address a wide range of error types, such as punctuation restoration and inverse text normalization, across long context. However, challenges remain regarding stability, controllability, completeness, and fluency. To mitigate these issues, this paper proposes the Chain of Correction (CoC), which uses a multi-turn chat format to correct errors segment by segment, guided by pre-recognized text and full-text context for better semantic understanding. Utilizing the open-sourced ChFT dataset, we fine-tune a pre-trained LLM to evaluate CoC's performance. Experiments show that CoC significantly outperforms baseline and benchmark systems in correcting full-text ASR outputs. We also analyze correction thresholds to balance under-correction and over-rephrasing, extrapolate CoC on extra-long ASR outputs, and explore using other types of information to guide error correction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_01519 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Chain of Correction for Full-text Speech Recognition with Large Language Models Tang, Zhiyuan Wang, Dong Zhou, Zhikai Liu, Yong Huang, Shen Shang, Shidong Computation and Language Audio and Speech Processing Full-text error correction with Large Language Models (LLMs) for Automatic Speech Recognition (ASR) is attracting increased attention for its ability to address a wide range of error types, such as punctuation restoration and inverse text normalization, across long context. However, challenges remain regarding stability, controllability, completeness, and fluency. To mitigate these issues, this paper proposes the Chain of Correction (CoC), which uses a multi-turn chat format to correct errors segment by segment, guided by pre-recognized text and full-text context for better semantic understanding. Utilizing the open-sourced ChFT dataset, we fine-tune a pre-trained LLM to evaluate CoC's performance. Experiments show that CoC significantly outperforms baseline and benchmark systems in correcting full-text ASR outputs. We also analyze correction thresholds to balance under-correction and over-rephrasing, extrapolate CoC on extra-long ASR outputs, and explore using other types of information to guide error correction. |
| title | Chain of Correction for Full-text Speech Recognition with Large Language Models |
| topic | Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2504.01519 |