mlsanityData to 7 Oct 2026

Improving Automatic Speech Recognition for Non-Native English with Transfer Learning and Language Model Decoding

arXiv 2202.05209 ↗First posted 10 Feb 2022cs.CL cs.SD eess.AScited by 3

Not on the map. Why?

Abstract (arXiv)

ASR systems designed for native English (L1) usually underperform on non-native English (L2). To address this performance gap, (i) we extend our previous work to investigate fine-tuning of a pre-trained wav2vec 2.0 model citebaevski2020wav2vec,xu2021self under a rich set of L1 and L2 training conditions. We further (ii) incorporate language model decoding in the ASR system, along with the fine-tuning method. Quantifying gains acquired from each of these two approaches separately and an error analysis allows us to identify different sources of improvement within our models. We find that while the large self-trained wav2vec 2.0 may be internalizing sufficient decoding knowledge for clean L1 speech citexu2021self, this does not hold for L2 speech and accounts for the utility of employing language model decoding on L2 data.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 34 of its 64 references that are in the map. First posted on arXiv 10 Feb 2022.

Builds on

34 of 64 references.

References · 34

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  4. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  5. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  6. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  7. 2015Listen, Attend and Spellcited by 542
  8. 2019Libri-Light: A Benchmark for ASR with Limited or No Supervisioncited by 462
  9. 2015Attention-Based Models for Speech Recognitioncited by 400
  10. 2019vq-wav2vec: Self-Supervised Learning of Discrete Speech Representationscited by 335
  11. 2019Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoderscited by 196
  12. 2019An Unsupervised Autoregressive Model for Speech Representation Learningcited by 185
22 more
  1. 2019End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architecturescited by 120
  2. 2020If beam search is the answer, what was the question?cited by 114
  3. 2020Self-training and Pre-training are Complementary for Speech Recognitioncited by 98
  4. 2019Transformer-based Acoustic Modeling for Hybrid Speech Recognitioncited by 86
  5. 2015EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decodingcited by 73
  6. 2021Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognitioncited by 68
  7. 2019Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognitioncited by 66
  8. 2020Training Speech Recognition Models with Federated Learning: A Quality/Cost Frameworkcited by 46
  9. 2018Domain Adversarial Training for Accented Speech Recognitioncited by 40
  10. 2020Distilling the Knowledge of BERT for Sequence-to-Sequence ASRcited by 38
  11. 2015Transfer Learning for Speech and Language Processingcited by 35
  12. 2014First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNscited by 27
  13. 2017Transfer Learning for Speech Recognition on a Budgetcited by 25
  14. 2021The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methodscited by 24
  15. 2018End-to-end Speech Recognition with Word-based RNN Language Modelscited by 23
  16. 2020REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabelingcited by 18
  17. 2021Best of Both Worlds: Robust Accented Speech Recognition with Adversarial Transfer Learningcited by 17
  18. 2021Federated Learning in ASR: Not as Easy as You Thinkcited by 14
  19. 2017Comparison of Decoding Strategies for CTC Acoustic Modelscited by 13
  20. 2021Speech Technology for Everyone: Automatic Speech Recognition for Non-Native English with Transfer Learningcited by 9
  21. 2018Non-native children speech recognition through transfer learningcited by 7
  22. 2016Character-Level Incremental Speech Recognition with Recurrent Neural Networkscited by 6

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 0; 2025: 1.

3 papers.

  1. 2023Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalizationcited by 28
  2. 2023A Deep Dive into the Disparity of Word Error Rates Across Thousands of NPTEL MOOC Videoscited by 5
  3. 2025Improving the Inclusivity of Dutch Speech Recognition by Fine-tuning Whisper on the JASMIN-CGN Corpuscited by 5