# Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correction

arXiv: https://arxiv.org/abs/2505.24347 · HTML: https://mlsanity.com/paper/2505.24347/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 30 May 2025.

## Builds on (most cited first, 26 of 26)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [Generated Knowledge Prompting for Commonsense Reasoning](https://mlsanity.com/paper/2110.08387/) (2021)
- [AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale](https://mlsanity.com/paper/1808.10583/) (2018)
- [WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit](https://mlsanity.com/paper/2102.01547/) (2021)
- [Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting](https://mlsanity.com/paper/2309.15649/) (2023)
- [Can Generative Large Language Models Perform ASR Error Correction?](https://mlsanity.com/paper/2307.04172/) (2023)
- [ASR Error Correction and Domain Adaptation Using Machine Translation](https://mlsanity.com/paper/2003.07692/) (2020)
- [FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition](https://mlsanity.com/paper/2105.03842/) (2021)
- [Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition](https://mlsanity.com/paper/2012.05481/) (2020)
- [N-LTP: An Open-source Neural Language Technology Platform for Chinese](https://mlsanity.com/paper/2009.11616/) (2020)
- [U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition](https://mlsanity.com/paper/2106.05642/) (2021)
- [FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition](https://mlsanity.com/paper/2109.14420/) (2021)
- [Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models](https://mlsanity.com/paper/2205.00176/) (2022)
- [ASR Error Correction using Large Language Models](https://mlsanity.com/paper/2409.09554/) (2024)
- [Learning from Past Mistakes: Improving Automatic Speech Recognition Output via Noisy-Clean Phrase Context Modeling](https://mlsanity.com/paper/1802.02607/) (2018)
- [Mask the Correct Tokens: An Embarrassingly Simple Approach for Error Correction](https://mlsanity.com/paper/2211.13252/) (2022)
- [SoftCorrect: Error Correction with Soft Detection for Automatic Speech Recognition](https://mlsanity.com/paper/2212.01039/) (2022)
- [A Survey on Open Information Extraction from Rule-based Model to Large Language Model](https://mlsanity.com/paper/2208.08690/) (2022)
- [Exploring the Integration of Large Language Models into Automatic Speech Recognition Systems: An Empirical Study](https://mlsanity.com/paper/2307.06530/) (2023)

## Built on by (most cited first, 7 of 7)

- [CantoASR: Prosody-Aware ASR-LALM Collaboration for Low-Resource Cantonese](https://mlsanity.com/paper/2511.04139/) (2025)
- [Speech-Hands: A Self-Reflection Voice Agentic Approach to Speech Recognition and Audio Reasoning with Omni Perception](https://mlsanity.com/paper/2601.09413/) (2026)
- [VoiceSHIELD-Small: Real-Time Malicious Speech Detection and Transcription](https://mlsanity.com/paper/2603.07708/) (2026)
- [Listening, Imagining & Refining: A Heuristic Optimized ASR Correction Framework with LLMs](https://mlsanity.com/paper/2509.15095/) (2025)
- [From Text Metrics to Model Internals: A Study of Whisper ASR Hallucination Detection](https://mlsanity.com/paper/2606.23060/) (2026)
- [Speech Recognition on TV Series with Video-guided Post-ASR Correction](https://mlsanity.com/paper/2506.07323/) (2025)
- [Graph-Based Phonetic Error Correction of Noisy ASR](https://mlsanity.com/paper/2606.24889/) (2026)

## Abstract (arXiv)

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.