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

• URL: http://arxiv.org/abs/2407.12817v1
• Date: Sat, 29 Jun 2024 17:56:28 GMT
• Title: Error Correction by Paying Attention to Both Acoustic and Confidence References for Automatic Speech Recognition
• Authors: Yuchun Shu, Bo Hu, Yifeng He, Hao Shi, Longbiao Wang, Jianwu Dang,
• Abstract summary: We propose a non-autoregressive speech error correction method. A Confidence Module measures the uncertainty of each word of the N-best ASR hypotheses. The proposed system reduces the error rate by 21% compared with the ASR model.
• Score: 52.624909026294105
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Tag and correct: high precision post-editing approach to correction of speech recognition errors [0.0]
  It consists of using a neural sequence tagger that learns how to correct an ASR (Automatic Speech Recognition) hypothesis word by word and a corrector module that applies corrections returned by the tagger. The proposed solution is applicable to any ASR system, regardless of its architecture, and provides high-precision control over errors being corrected.
  arXiv  Detail & Related papers  (2024-06-11T09:52:33Z)
• HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models [81.56455625624041]
  We introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction. The proposed benchmark contains a novel dataset, HyPoradise (HP), encompassing more than 334,000 pairs of N-best hypotheses. LLMs with reasonable prompt and its generative capability can even correct those tokens that are missing in N-best list.
  arXiv  Detail & Related papers  (2023-09-27T14:44:10Z)
• SoftCorrect: Error Correction with Soft Detection for Automatic Speech Recognition [116.31926128970585]
  We propose SoftCorrect with a soft error detection mechanism to avoid the limitations of both explicit and implicit error detection. Compared with implicit error detection with CTC loss, SoftCorrect provides explicit signal about which words are incorrect. Experiments on AISHELL-1 and Aidatatang datasets show that SoftCorrect achieves 26.1% and 9.4% CER reduction respectively.
  arXiv  Detail & Related papers  (2022-12-02T09:11:32Z)
• ASR Error Detection via Audio-Transcript entailment [1.3750624267664155]
  We propose an end-to-end approach for ASR error detection using audio-transcript entailment. The proposed model utilizes an acoustic encoder and a linguistic encoder to model the speech and transcript respectively. Our proposed model achieves classification error rates (CER) of 26.2% on all transcription errors and 23% on medical errors specifically, leading to improvements upon a strong baseline by 12% and 15.4%, respectively.
  arXiv  Detail & Related papers  (2022-07-22T02:47:15Z)
• RED-ACE: Robust Error Detection for ASR using Confidence Embeddings [5.4693121539705984]
  We propose to utilize the ASR system's word-level confidence scores for improving AED performance. We add an ASR Confidence Embedding layer to the AED model's encoder, allowing us to jointly encode the confidence scores and the transcribed text into a contextualized representation.
  arXiv  Detail & Related papers  (2022-03-14T15:13:52Z)
• End-to-end contextual asr based on posterior distribution adaptation for hybrid ctc/attention system [61.148549738631814]
  End-to-end (E2E) speech recognition architectures assemble all components of traditional speech recognition system into a single model. Although it simplifies ASR system, it introduces contextual ASR drawback: the E2E model has worse performance on utterances containing infrequent proper nouns. We propose to add a contextual bias attention (CBA) module to attention based encoder decoder (AED) model to improve its ability of recognizing the contextual phrases.
  arXiv  Detail & Related papers  (2022-02-18T03:26:02Z)
• Cross-Modal ASR Post-Processing System for Error Correction and Utterance Rejection [25.940199825317073]
  We propose a cross-modal post-processing system for speech recognizers. It fuses acoustic features and textual features from different modalities. It joints a confidence estimator and an error corrector in multi-task learning fashion.
  arXiv  Detail & Related papers  (2022-01-10T12:29:55Z)
• Improving Distinction between ASR Errors and Speech Disfluencies with Feature Space Interpolation [0.0]
  Fine-tuning pretrained language models (LMs) is a popular approach to automatic speech recognition (ASR) error detection during post-processing. This paper proposes a scheme to improve existing LM-based ASR error detection systems.
  arXiv  Detail & Related papers  (2021-08-04T02:11:37Z)
• FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition [90.34177266618143]
  We propose FastCorrect, a novel NAR error correction model based on edit alignment. FastCorrect speeds up the inference by 6-9 times and maintains the accuracy (8-14% WER reduction) compared with the autoregressive correction model. It outperforms the accuracy of popular NAR models adopted in neural machine translation by a large margin.
  arXiv  Detail & Related papers  (2021-05-09T05:35:36Z)
• Joint Contextual Modeling for ASR Correction and Language Understanding [60.230013453699975]
  We propose multi-task neural approaches to perform contextual language correction on ASR outputs jointly with language understanding (LU) We show that the error rates of off the shelf ASR and following LU systems can be reduced significantly by 14% relative with joint models trained using small amounts of in-domain data.
  arXiv  Detail & Related papers  (2020-01-28T22:09:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.