mlsanityData to 7 Oct 2026

Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training

arXiv 2011.13439 ↗First posted 26 Nov 2020cs.CL cs.LG cs.SDcited by 38

Not on the map. Why?

Abstract (arXiv)

The performance of automatic speech recognition (ASR) systems typically degrades significantly when the training and test data domains are mismatched. In this paper, we show that self-training (ST) combined with an uncertainty-based pseudo-label filtering approach can be effectively used for domain adaptation. We propose DUST, a dropout-based uncertainty-driven self-training technique which uses agreement between multiple predictions of an ASR system obtained for different dropout settings to measure the model's uncertainty about its prediction. DUST excludes pseudo-labeled data with high uncertainties from the training, which leads to substantially improved ASR results compared to ST without filtering, and accelerates the training time due to a reduced training data set. Domain adaptation experiments using WSJ as a source domain and TED-LIUM 3 as well as SWITCHBOARD as the target domains show that up to 80% of the performance of a system trained on ground-truth data can be recovered.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 16; 2023: 8; 2024: 6; 2025: 2; 2026: 2.

38 papers.

Sort:

By area:

  1. 2021Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Trainingcited by 148
  2. 2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
  3. 2021Momentum Pseudo-Labeling for Semi-Supervised Speech Recognitioncited by 37
  4. 2022Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognitioncited by 19
  5. 2021Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0cited by 12
  6. 2023In Search for a Generalizable Method for Source Free Domain Adaptationcited by 12
  7. 2022Boosting Cross-Domain Speech Recognition with Self-Supervisioncited by 10
  8. 2021Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matchingcited by 9
  9. 2022USTED: Improving ASR with a Unified Speech and Text Encoder-Decodercited by 7
  10. 2022Sample-Efficient Unsupervised Domain Adaptation of Speech Recognition Systems A case study for Modern Greekcited by 7
  11. 2023A Novel Self-training Approach for Low-resource Speech Recognitioncited by 7
  12. 2024Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Modelscited by 7
26 more
  1. 2024Self-Learning for Personalized Keyword Spotting on Ultra-Low-Power Audio Sensorscited by 7
  2. 2023OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarkingcited by 6
  3. 2023Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognitioncited by 6
  4. 2024AdapTable: Test-Time Adaptation for Tabular Data via Shift-Aware Uncertainty Calibrator and Label Distribution Handlercited by 6
  5. 2022Unsupervised domain adaptation for speech recognition with unsupervised error correctioncited by 5
  6. 2022Knowledge Distillation for Multi-Target Domain Adaptation in Real-Time Person Re-Identificationcited by 4
  7. 2023Test-Time Training for Speechcited by 4
  8. 2022Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Datacited by 3
  9. 2022Maximizing Conditional Independence for Unsupervised Domain Adaptationcited by 2
  10. 2023Entailment as Robust Self-Learnercited by 2
  11. 2022Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducercited by 1
  12. 2022On Unsupervised Uncertainty-Driven Speech Pseudo-Label Filtering and Model Calibrationcited by 1
  13. 2022Uncertainty Estimation in Deep Speech Enhancement Using Complex Gaussian Mixture Modelscited by 1
  14. 2025Customizing Speech Recognition Model with Large Language Model Feedbackcited by 1
  15. 2026ReHear: Iterative Pseudo-Label Refinement for Semi-Supervised Speech Recognition via Audio Large Language Modelscited by 1
  16. 2022Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environmentscited by 0
  17. 2022Learning Invariant Representation and Risk Minimized for Unsupervised Accent Domain Adaptationcited by 0
  18. 2022Investigating self-supervised, weakly supervised and fully supervised training approaches for multi-domain automatic speech recognition: a study on Bangladeshi Banglacited by 0
  19. 2022Training Autoregressive Speech Recognition Models with Limited in-domain Supervisioncited by 0
  20. 2023Integrating Uncertainty into Neural Network-based Speech Enhancementcited by 0
  21. 2023End-to-End Open Vocabulary Keyword Search With Multilingual Neural Representationscited by 0
  22. 2024Self-Train Before You Transcribecited by 0
  23. 2024Written Term Detection Improves Spoken Term Detectioncited by 0
  24. 2024Transliterated Zero-Shot Domain Adaptation for Automatic Speech Recognitioncited by 0
  25. 2025Robust Unsupervised Adaptation of a Speech Recogniser Using Entropy Minimisation and Speaker Codescited by 0
  26. 2026StreamHear: Domain-Adapted Pseudo-Labeling for Semi-Supervised Streaming Speech Recognitioncited by 0