mlsanityData to 7 Oct 2026

Domain Adversarial Training for Accented Speech Recognition

arXiv 1806.02786 ↗First posted 7 Jun 2018cs.CLcited by 40

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a domain adversarial training (DAT) algorithm to alleviate the accented speech recognition problem. In order to reduce the mismatch between labeled source domain data ("standard" accent) and unlabeled target domain data (with heavy accents), we augment the learning objective for a Kaldi TDNN network with a domain adversarial training (DAT) objective to encourage the model to learn accent-invariant features. In experiments with three Mandarin accents, we show that DAT yields up to 7.45% relative character error rate reduction when we do not have transcriptions of the accented speech, compared with the baseline trained on standard accent data only. We also find a benefit from DAT when used in combination with training from automatic transcriptions on the accented data. Furthermore, we find that DAT is superior to multi-task learning for accented speech recognition.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 11; 2023: 8; 2024: 4; 2025: 5; 2026: 3.

40 papers.

Sort:

By area:

  1. 2023AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASRcited by 34
  2. 2022Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognitioncited by 19
  3. 2022Improving Distortion Robustness of Self-supervised Speech Processing Tasks with Domain Adaptationcited by 16
  4. 2022A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairnesscited by 13
  5. 2024Adversarial Representation Engineering: A General Model Editing Framework for Large Language Modelscited by 12
  6. 2021Accented Speech Recognition: A Surveycited by 11
  7. 2021Supervised Contrastive Learning for Accented Speech Recognitioncited by 10
  8. 2021Differentiable Allophone Graphs for Language-Universal Speech Recognitioncited by 10
  9. 2022Boosting Cross-Domain Speech Recognition with Self-Supervisioncited by 10
  10. 2021Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matchingcited by 9
  11. 2021Understanding and Improvement of Adversarial Training for Network Embedding from an Optimization Perspectivecited by 9
  12. 2021Speech Technology for Everyone: Automatic Speech Recognition for Non-Native English with Transfer Learningcited by 9
28 more
  1. 2022Sample-Efficient Unsupervised Domain Adaptation of Speech Recognition Systems A case study for Modern Greekcited by 7
  2. 2023AfriNames: Most ASR models "butcher" African Namescited by 7
  3. 2023Advancing Test-Time Adaptation in Wild Acoustic Test Settingscited by 7
  4. 2022Enhancing and Adversarial: Improve ASR with Speaker Labelscited by 6
  5. 2023Accented Speech Recognition With Accent-specific Codebookscited by 6
  6. 2022Unsupervised domain adaptation for speech recognition with unsupervised error correctioncited by 5
  7. 2024Exploration of Adapter for Noise Robust Automatic Speech Recognitioncited by 4
  8. 2022Improving Automatic Speech Recognition for Non-Native English with Transfer Learning and Language Model Decodingcited by 3
  9. 2025Adapting Automatic Speech Recognition for Accented Air Traffic Control Communicationscited by 3
  10. 2021Error-driven Fixed-Budget ASR Personalization for Accented Speakerscited by 2
  11. 2022An Overview of Indian Spoken Language Recognition from Machine Learning Perspectivecited by 2
  12. 2024Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognitioncited by 2
  13. 2025Effects of Speaker Count, Duration, and Accent Diversity on Zero-Shot Accent Robustness in Low-Resource ASRcited by 2
  14. 2021Accented Speech Recognition Inspired by Human Perceptioncited by 1
  15. 2021Improving Adversarial Robustness for Free with Snapshot Ensemblecited by 1
  16. 2023MADI: Inter-domain Matching and Intra-domain Discrimination for Cross-domain Speech Recognitioncited by 1
  17. 2023Synthetic Cross-accent Data Augmentation for Automatic Speech Recognitioncited by 1
  18. 2025CO-VADA: A Confidence-Oriented Voice Augmentation Debiasing Approach for Fair Speech Emotion Recognitioncited by 1
  19. 2026Identifying and typifying demographic unfairness in phoneme-level embeddings of self-supervised speech recognition modelscited by 1
  20. 2022Hear No Evil: Towards Adversarial Robustness of Automatic Speech Recognition via Multi-Task Learningcited by 0
  21. 2022Speaker- and Age-Invariant Training for Child Acoustic Modeling Using Adversarial Multi-Task Learningcited by 0
  22. 2023Feature Normalization for Fine-tuning Self-Supervised Models in Speech Enhancementcited by 0
  23. 2023A meta learning scheme for fast accent domain expansion in Mandarin speech recognitioncited by 0
  24. 2024Language-Universal Speech Attributes Modeling for Zero-Shot Multilingual Spoken Keyword Recognitioncited by 0
  25. 2025Improving the Speaker Anonymization Evaluation's Robustness to Target Speakers with Adversarial Learningcited by 0
  26. 2025Proficiency-Aware Adaptation and Data Augmentation for Robust L2 ASRcited by 0
  27. 2026Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognitioncited by 0
  28. 2026Robust Generative Audio Quality Assessment: Disentangling Quality from Spurious Correlationscited by 0