mlsanityData to 13 Oct 2026

Error Correction by Paying Attention to Both Acoustic and Confidence References for Automatic Speech Recognition

arXiv 2407.12817 ↗First posted 29 Jun 2024cs.CL cs.SD eess.AScited by 2

Not on the map. Why?

Abstract (arXiv)

Accurately finding the wrong words in the automatic speech recognition (ASR) hypothesis and recovering them well-founded is the goal of speech error correction. In this paper, we propose a non-autoregressive speech error correction method. A Confidence Module measures the uncertainty of each word of the N-best ASR hypotheses as the reference to find the wrong word position. Besides, the acoustic feature from the ASR encoder is also used to provide the correct pronunciation references. N-best candidates from ASR are aligned using the edit path, to confirm each other and recover some missing character errors. Furthermore, the cross-attention mechanism fuses the information between error correction references and the ASR hypothesis. The experimental results show that both the acoustic and confidence references help with error correction. The proposed system reduces the error rate by 21% compared with the ASR model.

Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Builds on 20 of its 35 references that are in the map. First posted on arXiv 29 Jun 2024.

Builds on

20 of 35 references.

References · 20

  1. 2017Attention Is All You Needcited by 60,106
  2. 2017AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baselinecited by 366
  3. 2021WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkitcited by 123
  4. 2020Spelling Error Correction with Soft-Masked BERTcited by 90
  5. 2020Deliberation Model Based Two-Pass End-to-End Speech Recognitioncited by 57
  6. 2023Can Generative Large Language Models Perform ASR Error Correction?cited by 56
  7. 2020ASR Error Correction and Domain Adaptation Using Machine Translationcited by 48
  8. 2021FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognitioncited by 43
  9. 2023N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Spacecited by 41
  10. 2020Confidence Estimation for Attention-based Sequence-to-sequence Models for Speech Recognitioncited by 35
  11. 2021Transformer Based Deliberation for Two-Pass Speech Recognitioncited by 29
  12. 2021FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognitioncited by 27
8 more
  1. 2020Improving Readability for Automatic Speech Recognition Transcriptioncited by 22
  2. 2021Learning Word-Level Confidence For Subword End-to-End ASRcited by 22
  3. 2022Error Correction in ASR using Sequence-to-Sequence Modelscited by 19
  4. 2022Mask the Correct Tokens: An Embarrassingly Simple Approach for Error Correctioncited by 10
  5. 2022SoftCorrect: Error Correction with Soft Detection for Automatic Speech Recognitioncited by 9
  6. 2022Cross-Modal ASR Post-Processing System for Error Correction and Utterance Rejectioncited by 6
  7. 2024Exploration of Adapter for Noise Robust Automatic Speech Recognitioncited by 4
  8. 2022Acoustic-aware Non-autoregressive Spell Correction with Mask Sample Decodingcited by 1

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Serialized Output Prompting for Large Language Model-based Multi-Talker Speech Recognitioncited by 5
  2. 2025Data-Efficient ASR Personalization for Non-Normative Speech Using an Uncertainty-Based Phoneme Difficulty Score for Guided Samplingcited by 1