mlsanityData to 7 Oct 2026

N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Space

arXiv 2303.00456 ↗First posted 1 Mar 2023cs.CL cs.SD eess.AScited by 41

Not on the map. Why?

Abstract (arXiv)

Error correction models form an important part of Automatic Speech Recognition (ASR) post-processing to improve the readability and quality of transcriptions. Most prior works use the 1-best ASR hypothesis as input and therefore can only perform correction by leveraging the context within one sentence. In this work, we propose a novel N-best T5 model for this task, which is fine-tuned from a T5 model and utilizes ASR N-best lists as model input. By transferring knowledge from the pre-trained language model and obtaining richer information from the ASR decoding space, the proposed approach outperforms a strong Conformer-Transducer baseline. Another issue with standard error correction is that the generation process is not well-guided. To address this a constrained decoding process, either based on the N-best list or an ASR lattice, is used which allows additional information to be propagated.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). Builds on 16 of its 29 references that are in the map. First posted on arXiv 1 Mar 2023.

Builds on

16 of 29 references.

References · 16

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  3. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  4. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  5. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
  6. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  7. 2015Listen, Attend and Spellcited by 542
  8. 2019A spelling correction model for end-to-end speech recognitioncited by 63
  9. 2019Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Modelcited by 52
  10. 2020Joint Contextual Modeling for ASR Correction and Language Understandingcited by 30
  11. 2021FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognitioncited by 27
  12. 2020Less Is More: Improved RNN-T Decoding Using Limited Label Context and Path Mergingcited by 26
4 more
  1. 2021BART based semantic correction for Mandarin automatic speech recognition systemcited by 20
  2. 2022Error Correction in ASR using Sequence-to-Sequence Modelscited by 19
  3. 2019Lattice Transformer for Speech Translationcited by 15
  4. 2019Automatic Spelling Correction with Transformer for CTC-based End-to-End Speech Recognitioncited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 16; 2025: 13; 2026: 4.

41 papers.

Sort:

By area:

  1. 2023SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translationcited by 75
  2. 2023Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Promptingcited by 71
  3. 2023Can Generative Large Language Models Perform ASR Error Correction?cited by 56
  4. 2023Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognitioncited by 56
  5. 2023HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Modelscited by 41
  6. 2024Large Language Models are Efficient Learners of Noise-Robust Speech Recognitioncited by 30
  7. 2024ASR Error Correction using Large Language Modelscited by 23
  8. 2024GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translatorscited by 22
  9. 2023Multi-stage Large Language Model Correction for Speech Recognitioncited by 13
  10. 2024Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Modelscited by 13
  11. 2024Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognitioncited by 10
  12. 2024Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentationcited by 9
29 more
  1. 2024ASR-EC Benchmark: Evaluating Large Language Models on Chinese ASR Error Correctioncited by 7
  2. 2024Revisiting ASR Error Correction with Specialized Modelscited by 5
  3. 2024ProGRes: Prompted Generative Rescoring on ASR n-Bestcited by 5
  4. 2025Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognitioncited by 5
  5. 2025GEC-RAG: Improving Generative Error Correction via Retrieval-Augmented Generation for Automatic Speech Recognition Systemscited by 5
  6. 2023Adapting an Unadaptable ASR Systemcited by 3
  7. 2024Robust ASR Error Correction with Conservative Data Filteringcited by 3
  8. 2024Evolutionary Prompt Design for LLM-Based Post-ASR Error Correctioncited by 3
  9. 2024Full-text Error Correction for Chinese Speech Recognition with Large Language Modelcited by 3
  10. 2024MathSpeech: Leveraging Small LMs for Accurate Conversion in Mathematical Speech-to-Formulacited by 3
  11. 2025LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriorscited by 3
  12. 2025CantoASR: Prosody-Aware ASR-LALM Collaboration for Low-Resource Cantonesecited by 3
  13. 2023Harnessing the Zero-Shot Power of Instruction-Tuned Large Language Model in End-to-End Speech Recognitioncited by 2
  14. 2024Error Correction by Paying Attention to Both Acoustic and Confidence References for Automatic Speech Recognitioncited by 2
  15. 2024PERL: Pinyin Enhanced Rephrasing Language Model for Chinese ASR N-best Error Correctioncited by 1
  16. 2025FlanEC: Exploring Flan-T5 for Post-ASR Error Correctioncited by 1
  17. 2025Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentencescited by 1
  18. 2025Listening, Imagining & Refining: A Heuristic Optimized ASR Correction Framework with LLMscited by 1
  19. 2025Vision Language Models Are Not (Yet) Spelling Correctorscited by 1
  20. 2025Confidence-Guided Error Correction for Disordered Speech Recognitioncited by 1
  21. 2024Pinyin Regularization in Error Correction for Chinese Speech Recognition with Large Language Modelscited by 0
  22. 2025Chain of Correction for Full-text Speech Recognition with Large Language Modelscited by 0
  23. 2025Auto Review: Second Stage Error Detection for Highly Accurate Information Extraction from Phone Conversationscited by 0
  24. 2025Generative Annotation for ASR Named Entity Correctioncited by 0
  25. 2025Game-Oriented ASR Error Correction via RAG-Enhanced LLMcited by 0
  26. 2026RECOVER: Robust Entity Correction via agentic Orchestration of hypothesis Variants for Evidence-based Recoverycited by 0
  27. 2026Voice Memory for Agentic Speech Recognitioncited by 0
  28. 2026Listen to the Latents: Self-Correcting Speech Recognition in Large Audio Language Models Through Hidden-State Interactionscited by 0
  29. 2026Leveraging Fine-grained Error Correction in Korean Speech Recognition for Consultation Servicescited by 0