mlsanityData to 7 Oct 2026

Can Generative Large Language Models Perform ASR Error Correction?

arXiv 2307.04172 ↗First posted 9 Jul 2023cs.CL cs.SD eess.AScited by 56

Not on the map. Why?

Abstract (arXiv)

ASR error correction is an interesting option for post processing speech recognition system outputs. These error correction models are usually trained in a supervised fashion using the decoding results of a target ASR system. This approach can be computationally intensive and the model is tuned to a specific ASR system. Recently generative large language models (LLMs) have been applied to a wide range of natural language processing tasks, as they can operate in a zero-shot or few shot fashion. In this paper we investigate using ChatGPT, a generative LLM, for ASR error correction. Based on the ASR N-best output, we propose both unconstrained and constrained, where a member of the N-best list is selected, approaches. Additionally, zero and 1-shot settings are evaluated. Experiments show that this generative LLM approach can yield performance gains for two different state-of-the-art ASR architectures, transducer and attention-encoder-decoder based, and multiple test sets.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). Builds on 24 of its 37 references that are in the map. First posted on arXiv 9 Jul 2023.

Builds on

24 of 37 references.

References · 24

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  6. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  7. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  8. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  9. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  10. 2023PaLM 2 Technical Reportcited by 1,154
  11. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  12. 2015Listen, Attend and Spellcited by 542
12 more
  1. 2015Deep Speech 2: End-to-End Speech Recognition in English and Mandarincited by 449
  2. 2018TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptationcited by 224
  3. 2023Is ChatGPT a Highly Fluent Grammatical Error Correction System? A Comprehensive Evaluationcited by 97
  4. 2020Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognitioncited by 80
  5. 2023ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmarkcited by 77
  6. 2019A spelling correction model for end-to-end speech recognitioncited by 63
  7. 2019Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Modelcited by 52
  8. 2023N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Spacecited by 41
  9. 2021FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognitioncited by 27
  10. 2021BART based semantic correction for Mandarin automatic speech recognition systemcited by 20
  11. 2021N-Best ASR Transformer: Enhancing SLU Performance using Multiple ASR Hypothesescited by 12
  12. 2023Adapting an Unadaptable ASR Systemcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 24; 2025: 19; 2026: 7.

56 papers.

Sort:

By area:

  1. 2023Connecting Speech Encoder and Large Language Model for ASRcited by 79
  2. 2024SpeechVerse: A Large-scale Generalizable Audio Language Modelcited by 62
  3. 2024ASR Error Correction using Large Language Modelscited by 23
  4. 2024GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translatorscited by 22
  5. 2024Resilience of Large Language Models for Noisy Instructionscited by 20
  6. 2024The Sound of Healthcare: Improving Medical Transcription ASR Accuracy with Large Language Modelscited by 17
  7. 2024Performance evaluation of SLAM-ASR: The Good, the Bad, the Ugly, and the Way Forwardcited by 17
  8. 2023Leveraging Large Language Models for Exploiting ASR Uncertaintycited by 15
  9. 2023Multi-stage Large Language Model Correction for Speech Recognitioncited by 13
  10. 2024Unveiling the Potential of LLM-Based ASR on Chinese Open-Source Datasetscited by 13
  11. 2024Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentationcited by 9
  12. 2025When Large Language Models Meet Speech: A Survey on Integration Approachescited by 9
38 more
  1. 2025Evaluation of LLMs in Speech is Often Flawed: Test Set Contamination in Large Language Models for Speech Recognitioncited by 9
  2. 2024SALSA: Speedy ASR-LLM Synchronous Aggregationcited by 8
  3. 2026Text-only adaptation in LLM-based ASR through text denoisingcited by 8
  4. 2024ASR-EC Benchmark: Evaluating Large Language Models on Chinese ASR Error Correctioncited by 7
  5. 2025Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correctioncited by 7
  6. 2023Corpus Synthesis for Zero-shot ASR domain Adaptation using Large Language Modelscited by 5
  7. 2024ProGRes: Prompted Generative Rescoring on ASR n-Bestcited by 5
  8. 2025GEC-RAG: Improving Generative Error Correction via Retrieval-Augmented Generation for Automatic Speech Recognition Systemscited by 5
  9. 2025Leveraging LLM and Self-Supervised Training Models for Speech Recognition in Chinese Dialects: A Comparative Analysiscited by 5
  10. 2025Better Pseudo-labeling with Multi-ASR Fusion and Error Correction by SpeechLLMcited by 5
  11. 2024Towards interfacing large language models with ASR systems using confidence measures and promptingcited by 4
  12. 2024LA-RAG:Enhancing LLM-based ASR Accuracy with Retrieval-Augmented Generationcited by 4
  13. 2025Neural Spelling: A Spell-Based BCI System for Language Neural Decodingcited by 4
  14. 2025DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correctioncited by 4
  15. 2024Robust ASR Error Correction with Conservative Data Filteringcited by 3
  16. 2024Large Language Model Should Understand Pinyin for Chinese ASR Error Correctioncited by 3
  17. 2024MathSpeech: Leveraging Small LMs for Accurate Conversion in Mathematical Speech-to-Formulacited by 3
  18. 2025LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriorscited by 3
  19. 2025LLM-based Generative Error Correction for Rare Words with Synthetic Data and Phonetic Contextcited by 3
  20. 2025LLM-based phoneme-to-grapheme for phoneme-based speech recognitioncited by 3
  21. 2023Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model in End-to-End Speech Recognitioncited by 2
  22. 2024Error Correction by Paying Attention to Both Acoustic and Confidence References for Automatic Speech Recognitioncited by 2
  23. 2024Recording for Eyes, Not Echoing to Ears: Contextualized Spoken-to-Written Conversion of ASR Transcriptscited by 2
  24. 2024Are Transformers in Pre-trained LM A Good ASR Encoder? An Empirical Studycited by 2
  25. 2024Improving Grapheme-to-Phoneme Conversion through In-Context Knowledge Retrieval with Large Language Modelscited by 2
  26. 2025Retrieval-Augmented Speech Recognition Approach for Domain Challengescited by 2
  27. 2025PreMind: Multi-Agent Video Understanding for Advanced Indexing of Presentation-style Videoscited by 2
  28. 2025Large Language Models based ASR Error Correction for Child Conversationscited by 2
  29. 2025Re-evaluating Minimum Bayes Risk Decoding for Automatic Speech Recognitioncited by 2
  30. 2026Reducing Prompt Sensitivity in LLM-based Speech Recognition Through Learnable Projectioncited by 2
  31. 2023HypR: A comprehensive study for ASR hypothesis revising with a reference corpuscited by 1
  32. 2024Speech Prefix-Tuning with RNNT Loss for Improving LLM Predictionscited by 1
  33. 2024wav2graph: A Framework for Supervised Learning Knowledge Graph from Speechcited by 1
  34. 2024A Pilot Study of Applying Sequence-to-Sequence Voice Conversion to Evaluate the Intelligibility of L2 Speech Using a Native Speaker's Shadowingscited by 1
  35. 2024Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLMcited by 1
  36. 2025Optimizing Estonian TV Subtitles with Semi-supervised Learning and LLMscited by 1
  37. 2025PHRASED: Phrase Dictionary Biasing for Speech Translationcited by 1
  38. 2025Customizing Speech Recognition Model with Large Language Model Feedbackcited by 1

50 most cited of 56 All 56 (JSON)