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

arXiv: https://arxiv.org/abs/2011.13439 · HTML: https://mlsanity.com/paper/2011.13439/

## Key facts

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

## Built on by (most cited first, 30 of 38)

- [Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training](https://mlsanity.com/paper/2104.01027/) (2021)
- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition](https://mlsanity.com/paper/2106.08922/) (2021)
- [Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition](https://mlsanity.com/paper/2203.14222/) (2022)
- [Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0](https://mlsanity.com/paper/2110.03560/) (2021)
- [In Search for a Generalizable Method for Source Free Domain Adaptation](https://mlsanity.com/paper/2302.06658/) (2023)
- [Boosting Cross-Domain Speech Recognition with Self-Supervision](https://mlsanity.com/paper/2206.09783/) (2022)
- [Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching](https://mlsanity.com/paper/2104.07491/) (2021)
- [USTED: Improving ASR with a Unified Speech and Text Encoder-Decoder](https://mlsanity.com/paper/2202.06045/) (2022)
- [Sample-Efficient Unsupervised Domain Adaptation of Speech Recognition Systems A case study for Modern Greek](https://mlsanity.com/paper/2301.00304/) (2022)
- [A Novel Self-training Approach for Low-resource Speech Recognition](https://mlsanity.com/paper/2308.05269/) (2023)
- [Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models](https://mlsanity.com/paper/2405.14161/) (2024)
- [Self-Learning for Personalized Keyword Spotting on Ultra-Low-Power Audio Sensors](https://mlsanity.com/paper/2408.12481/) (2024)
- [OOD-Speech: A Large Bengali Speech Recognition Dataset for Out-of-Distribution Benchmarking](https://mlsanity.com/paper/2305.09688/) (2023)
- [Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition](https://mlsanity.com/paper/2308.06547/) (2023)
- [AdapTable: Test-Time Adaptation for Tabular Data via Shift-Aware Uncertainty Calibrator and Label Distribution Handler](https://mlsanity.com/paper/2407.10784/) (2024)
- [Unsupervised domain adaptation for speech recognition with unsupervised error correction](https://mlsanity.com/paper/2209.12043/) (2022)
- [Knowledge Distillation for Multi-Target Domain Adaptation in Real-Time Person Re-Identification](https://mlsanity.com/paper/2205.06237/) (2022)
- [Test-Time Training for Speech](https://mlsanity.com/paper/2309.10930/) (2023)
- [Joint Speech Transcription and Translation: Pseudo-Labeling with Out-of-Distribution Data](https://mlsanity.com/paper/2212.09982/) (2022)
- [Maximizing Conditional Independence for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2203.03212/) (2022)
- [Entailment as Robust Self-Learner](https://mlsanity.com/paper/2305.17197/) (2023)
- [Multiple-hypothesis RNN-T Loss for Unsupervised Fine-tuning and Self-training of Neural Transducer](https://mlsanity.com/paper/2207.14736/) (2022)
- [On Unsupervised Uncertainty-Driven Speech Pseudo-Label Filtering and Model Calibration](https://mlsanity.com/paper/2211.07795/) (2022)
- [Uncertainty Estimation in Deep Speech Enhancement Using Complex Gaussian Mixture Models](https://mlsanity.com/paper/2212.04831/) (2022)
- [Customizing Speech Recognition Model with Large Language Model Feedback](https://mlsanity.com/paper/2506.11091/) (2025)
- [ReHear: Iterative Pseudo-Label Refinement for Semi-Supervised Speech Recognition via Audio Large Language Models](https://mlsanity.com/paper/2602.18721/) (2026)
- [Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments](https://mlsanity.com/paper/2207.07273/) (2022)
- [Learning Invariant Representation and Risk Minimized for Unsupervised Accent Domain Adaptation](https://mlsanity.com/paper/2210.08182/) (2022)
- [Investigating self-supervised, weakly supervised and fully supervised training approaches for multi-domain automatic speech recognition: a study on Bangladeshi Bangla](https://mlsanity.com/paper/2210.12921/) (2022)

## 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.