Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correction
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_ | 1866914215983316992 |
|---|---|
| author | Fang, Yangui Chen, Baixu Peng, Jing Li, Xu Xi, Yu Zhang, Chengwei Zhong, Guohui |
| author_facet | Fang, Yangui Chen, Baixu Peng, Jing Li, Xu Xi, Yu Zhang, Chengwei Zhong, Guohui |
| contents | Automatic Speech Recognition (ASR) error correction aims to correct recognition errors while preserving accurate text. Although traditional approaches demonstrate moderate effectiveness, LLMs offer a paradigm that eliminates the need for training and labeled data. However, directly using LLMs will encounter hallucinations problem, which may lead to the modification of the correct text. To address this problem, we propose the Reliable LLM Correction Framework (RLLM-CF), which consists of three stages: (1) error pre-detection, (2) chain-of-thought sub-tasks iterative correction, and (3) reasoning process verification. The advantage of our method is that it does not require additional information or fine-tuning of the model, and ensures the correctness of the LLM correction under multi-pass programming. Experiments on AISHELL-1, AISHELL-2, and Librispeech show that the GPT-4o model enhanced by our framework achieves 21%, 11%, 9%, and 11.4% relative reductions in CER/WER. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_24347 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correction Fang, Yangui Chen, Baixu Peng, Jing Li, Xu Xi, Yu Zhang, Chengwei Zhong, Guohui Computation and Language Audio and Speech Processing Automatic Speech Recognition (ASR) error correction aims to correct recognition errors while preserving accurate text. Although traditional approaches demonstrate moderate effectiveness, LLMs offer a paradigm that eliminates the need for training and labeled data. However, directly using LLMs will encounter hallucinations problem, which may lead to the modification of the correct text. To address this problem, we propose the Reliable LLM Correction Framework (RLLM-CF), which consists of three stages: (1) error pre-detection, (2) chain-of-thought sub-tasks iterative correction, and (3) reasoning process verification. The advantage of our method is that it does not require additional information or fine-tuning of the model, and ensures the correctness of the LLM correction under multi-pass programming. Experiments on AISHELL-1, AISHELL-2, and Librispeech show that the GPT-4o model enhanced by our framework achieves 21%, 11%, 9%, and 11.4% relative reductions in CER/WER. |
| title | Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correction |
| topic | Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2505.24347 |