# Continual Test-time Adaptation for End-to-end Speech Recognition on Noisy Speech

arXiv: https://arxiv.org/abs/2406.11064 · HTML: https://mlsanity.com/paper/2406.11064/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jun 2024.

## Built on by (most cited first, 12 of 12)

- [DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment](https://mlsanity.com/paper/2507.02768/) (2025)
- [E-BATS: Efficient Backpropagation-Free Test-Time Adaptation for Speech Foundation Models](https://mlsanity.com/paper/2506.07078/) (2025)
- [SUTA-LM: Bridging Test-Time Adaptation and Language Model Rescoring for Robust ASR](https://mlsanity.com/paper/2506.11121/) (2025)
- [An Investigation of Test-time Adaptation for Audio Classification under Background Noise](https://mlsanity.com/paper/2507.15523/) (2025)
- [Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions](https://mlsanity.com/paper/2607.08164/) (2026)
- [DHAuDS: A Dynamic and Heterogeneous Audio Benchmark for Test-Time Adaptation](https://mlsanity.com/paper/2511.18421/) (2025)
- [Test-Time Adaptation for Speech Emotion Recognition](https://mlsanity.com/paper/2601.16240/) (2026)
- [Test-Time Adaptation for EEG Foundation Models: A Systematic Study under Real-World Distribution Shifts](https://mlsanity.com/paper/2604.16926/) (2026)
- [StarDrinks: An English and Korean Test Set for SLU Evaluation in a Drink Ordering Scenario](https://mlsanity.com/paper/2604.26500/) (2026)
- [Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models](https://mlsanity.com/paper/2605.08186/) (2026)
- [A Decision-Theoretic View of Test-Time Training: When, How Far, and Which Directions to Adapt](https://mlsanity.com/paper/2606.15569/) (2026)
- [TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMs](https://mlsanity.com/paper/2608.18386/) (2026)

## Abstract (arXiv)

Deep Learning-based end-to-end Automatic Speech Recognition (ASR) has made significant strides but still struggles with performance on out-of-domain samples due to domain shifts in real-world scenarios. Test-Time Adaptation (TTA) methods address this issue by adapting models using test samples at inference time. However, current ASR TTA methods have largely focused on non-continual TTA, which limits cross-sample knowledge learning compared to continual TTA. In this work, we first propose a Fast-slow TTA framework for ASR that leverages the advantage of continual and non-continual TTA. Following this framework, we introduce Dynamic SUTA (DSUTA), an entropy-minimization-based continual TTA method for ASR. To enhance DSUTA robustness for time-varying data, we design a dynamic reset strategy to automatically detect domain shifts and reset the model, making it more effective at handling multi-domain data. Our method demonstrates superior performance on various noisy ASR datasets, outperforming both non-continual and continual TTA baselines while maintaining robustness to domain changes without requiring domain boundary information.