mlsanityData to 7 Oct 2026

BART based semantic correction for Mandarin automatic speech recognition system

arXiv 2104.05507 ↗First posted 26 Mar 2021cs.CL cs.SD eess.AScited by 20

Not on the map. Why?

Abstract (arXiv)

Although automatic speech recognition (ASR) systems achieved significantly improvements in recent years, spoken language recognition error occurs which can be easily spotted by human beings. Various language modeling techniques have been developed on post recognition tasks like semantic correction. In this paper, we propose a Transformer based semantic correction method with pretrained BART initialization, Experiments on 10000 hours Mandarin speech dataset show that character error rate (CER) can be effectively reduced by 21.7% relatively compared to our baseline ASR system. Expert evaluation demonstrates that actual improvement of our model surpasses what CER indicates.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 13 of its 23 references that are in the map. First posted on arXiv 26 Mar 2021.

Builds on

13 of 23 references.

References · 13

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  6. 2020Pre-trained Models for Natural Language Processing: A Surveycited by 504
  7. 2017AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baselinecited by 364
  8. 2020Spelling Error Correction with Soft-Masked BERTcited by 90
  9. 2019Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Modelcited by 52
  10. 2020ASR Error Correction and Domain Adaptation Using Machine Translationcited by 48
  11. 2015THCHS-30 : A Free Chinese Speech Corpuscited by 43
  12. 2020Joint Contextual Modeling for ASR Correction and Language Understandingcited by 30
1 more
  1. 2018A novel pyramidal-FSMN architecture with lattice-free MMI for speech recognitioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 9; 2024: 5; 2025: 2; 2026: 1.

20 papers.

Sort:

  1. 2023Can Generative Large Language Models Perform ASR Error Correction?cited by 56
  2. 2023N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Spacecited by 41
  3. 2023HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Modelscited by 41
  4. 2024ASR Error Correction using Large Language Modelscited by 23
  5. 2023ed-cec: improving rare word recognition using asr postprocessing based on error detection and context-aware error correctioncited by 7
  6. 2024ASR-EC Benchmark: Evaluating Large Language Models on Chinese ASR Error Correctioncited by 7
  7. 2022ASR Error Correction with Constrained Decoding on Operation Predictioncited by 6
  8. 2022Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LMcited by 6
  9. 2022Unsupervised domain adaptation for speech recognition with unsupervised error correctioncited by 5
  10. 2024Revisiting ASR Error Correction with Specialized Modelscited by 5
  11. 2023Adapting an Unadaptable ASR Systemcited by 3
  12. 2024Robust ASR Error Correction with Conservative Data Filteringcited by 3
8 more
  1. 2024MathSpeech: Leveraging Small LMs for Accurate Conversion in Mathematical Speech-to-Formulacited by 3
  2. 2025CantoASR: Prosody-Aware ASR-LALM Collaboration for Low-Resource Cantonesecited by 3
  3. 2023Enhancing conversational quality in language learning chatbots: An evaluation of GPT4 for ASR error correctioncited by 2
  4. 2023Multiple Representation Transfer from Large Language Models to End-to-End ASR Systemscited by 2
  5. 2023Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-Augmentingcited by 2
  6. 2023HypR: A comprehensive study for ASR hypothesis revising with a reference corpuscited by 1
  7. 2025PMF-CEC: Phoneme-augmented Multimodal Fusion for Context-aware ASR Error Correction with Error-specific Selective Decodingcited by 1
  8. 2026Listen, Attend, Understand: a Regularization Technique for Stable E2E Speech Translation Training on High Variance labelscited by 0