# ASR Error Correction using Large Language Models

arXiv: https://arxiv.org/abs/2409.09554 · HTML: https://mlsanity.com/paper/2409.09554/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 55 references that are in the map.
- First posted on arXiv 14 Sep 2024.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://mlsanity.com/paper/1512.02595/) (2015)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark](https://mlsanity.com/paper/2310.18018/) (2023)
- [Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages](https://mlsanity.com/paper/2303.01037/) (2023)
- [TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation](https://mlsanity.com/paper/1805.04699/) (2018)
- [Task Contamination: Language Models May Not Be Few-Shot Anymore](https://mlsanity.com/paper/2312.16337/) (2023)
- [Is ChatGPT a Highly Fluent Grammatical Error Correction System? A Comprehensive Evaluation](https://mlsanity.com/paper/2304.01746/) (2023)
- [Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition](https://mlsanity.com/paper/2011.01991/) (2020)
- [ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmark](https://mlsanity.com/paper/2303.13648/) (2023)
- [A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognition](https://mlsanity.com/paper/2002.11268/) (2020)
- [A spelling correction model for end-to-end speech recognition](https://mlsanity.com/paper/1902.07178/) (2019)
- [Can Generative Large Language Models Perform ASR Error Correction?](https://mlsanity.com/paper/2307.04172/) (2023)
- [Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Model](https://mlsanity.com/paper/1910.10697/) (2019)
- [ASR Error Correction and Domain Adaptation Using Machine Translation](https://mlsanity.com/paper/2003.07692/) (2020)
- [Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models](https://mlsanity.com/paper/2311.06233/) (2023)
- [N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Space](https://mlsanity.com/paper/2303.00456/) (2023)
- [HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models](https://mlsanity.com/paper/2309.15701/) (2023)
- [FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition](https://mlsanity.com/paper/2109.14420/) (2021)
- [Investigating Methods to Improve Language Model Integration for Attention-based Encoder-Decoder ASR Models](https://mlsanity.com/paper/2104.05544/) (2021)
- [BART based semantic correction for Mandarin automatic speech recognition system](https://mlsanity.com/paper/2104.05507/) (2021)
- [Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Models](https://mlsanity.com/paper/2405.10025/) (2024)
- [N-Best ASR Transformer: Enhancing SLU Performance using Multiple ASR Hypotheses](https://mlsanity.com/paper/2106.06519/) (2021)

## Built on by (most cited first, 24 of 24)

- [Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correction](https://mlsanity.com/paper/2505.24347/) (2025)
- [GEC-RAG: Improving Generative Error Correction via Retrieval-Augmented Generation for Automatic Speech Recognition Systems](https://mlsanity.com/paper/2501.10734/) (2025)
- [CantoASR: Prosody-Aware ASR-LALM Collaboration for Low-Resource Cantonese](https://mlsanity.com/paper/2511.04139/) (2025)
- [PSRB: A Comprehensive Benchmark for Evaluating Persian ASR Systems](https://mlsanity.com/paper/2505.21230/) (2025)
- [When AVSR Meets Video Conferencing: Dataset, Degradation, and the Hidden Mechanism Behind Performance Collapse](https://mlsanity.com/paper/2603.22915/) (2026)
- [Enhancing Multilingual LLM-based ASR with Mixture of Experts and Dynamic Downsampling](https://mlsanity.com/paper/2606.10439/) (2026)
- [PMF-CEC: Phoneme-augmented Multimodal Fusion for Context-aware ASR Error Correction with Error-specific Selective Decoding](https://mlsanity.com/paper/2506.11064/) (2025)
- [Customizing Speech Recognition Model with Large Language Model Feedback](https://mlsanity.com/paper/2506.11091/) (2025)
- [Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences](https://mlsanity.com/paper/2508.03542/) (2025)
- [Listening, Imagining & Refining: A Heuristic Optimized ASR Correction Framework with LLMs](https://mlsanity.com/paper/2509.15095/) (2025)
- [Lost in Transcription: How Speech-to-Text Errors Derail Code Understanding](https://mlsanity.com/paper/2601.15339/) (2026)
- [Improving Speech Recognition of Named Entities in Classroom Speech with LLM Revision and Phonetic-Semantic Context](https://mlsanity.com/paper/2506.10779/) (2025)
- [Bridging ASR and LLMs for Dysarthric Speech Recognition: Benchmarking Self-Supervised and Generative Approaches](https://mlsanity.com/paper/2508.08027/) (2025)
- [Context-Enhanced Granular Edit Representation for Efficient and Accurate ASR Post-editing](https://mlsanity.com/paper/2509.14263/) (2025)
- [Game-Oriented ASR Error Correction via RAG-Enhanced LLM](https://mlsanity.com/paper/2509.23630/) (2025)
- [On the Difficulty of Token-Level Modeling of Dysfluency and Fluency Shaping Artifacts](https://mlsanity.com/paper/2512.02027/) (2025)
- [From Speech to Subtitles: Evaluating ASR Models in Subtitling Italian Television Programs](https://mlsanity.com/paper/2512.19161/) (2025)
- [VALLR-Pin: Uncertainty-Factorized Visual Speech Recognition for Mandarin with Pinyin Guidance](https://mlsanity.com/paper/2512.20032/) (2025)
- [RECOVER: Robust Entity Correction via agentic Orchestration of hypothesis Variants for Evidence-based Recovery](https://mlsanity.com/paper/2603.16411/) (2026)
- [Can Large Language Models Reliably Correct Errors in Low-Resource ASR? A Contamination-Aware Case Study on West Frisian](https://mlsanity.com/paper/2605.19711/) (2026)
- [Diarization-Guided Qwen-ASR Adaptation for Multilingual Two-Speaker Conversational Speech](https://mlsanity.com/paper/2607.08208/) (2026)
- [Leveraging Fine-grained Error Correction in Korean Speech Recognition for Consultation Services](https://mlsanity.com/paper/2609.09889/) (2026)
- [Model-Agnostic and Language-Agnostic Voice Pipeline Improvement for the Agriculture Domain](https://mlsanity.com/paper/2609.20504/) (2026)
- [Select or Rewrite: Oracle-Guided Fine-Tuning for Generative ASR Post-Editing from N-Best Hypotheses](https://mlsanity.com/paper/2610.15056/) (2026)

## Abstract (arXiv)

Error correction (EC) models play a crucial role in refining Automatic Speech Recognition (ASR) transcriptions, enhancing the readability and quality of transcriptions. Without requiring access to the underlying code or model weights, EC can improve performance and provide domain adaptation for black-box ASR systems. This work investigates the use of large language models (LLMs) for error correction across diverse scenarios. 1-best ASR hypotheses are commonly used as the input to EC models. We propose building high-performance EC models using ASR N-best lists which should provide more contextual information for the correction process. Additionally, the generation process of a standard EC model is unrestricted in the sense that any output sequence can be generated. For some scenarios, such as unseen domains, this flexibility may impact performance. To address this, we introduce a constrained decoding approach based on the N-best list or an ASR lattice. Finally, most EC models are trained for a specific ASR system requiring retraining whenever the underlying ASR system is changed. This paper explores the ability of EC models to operate on the output of different ASR systems. This concept is further extended to zero-shot error correction using LLMs, such as ChatGPT. Experiments on three standard datasets demonstrate the efficacy of our proposed methods for both Transducer and attention-based encoder-decoder ASR systems. In addition, the proposed method can serve as an effective method for model ensembling.