# Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition arXiv: https://arxiv.org/abs/2203.14222 ยท HTML: https://mlsanity.com/paper/2203.14222/ ## Key facts - Cited by 19 papers in the map (data through 14 Oct 2026). - Builds on 24 of its 34 references that are in the map. - First posted on arXiv 27 Mar 2022. ## Builds on (most cited first, 24 of 24) - [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020) - [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019) - [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019) - [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019) - [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020) - [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018) - [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021) - [W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training](https://mlsanity.com/paper/2108.06209/) (2021) - [Semi-supervised Domain Adaptation via Minimax Entropy](https://mlsanity.com/paper/1904.06487/) (2019) - [TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation](https://mlsanity.com/paper/1805.04699/) (2018) - [A DIRT-T Approach to Unsupervised Domain Adaptation](https://mlsanity.com/paper/1802.08735/) (2018) - [Domain Adaptation for Semantic Segmentation with Maximum Squares Loss](https://mlsanity.com/paper/1909.13589/) (2019) - [AutoDIAL: Automatic DomaIn Alignment Layers](https://mlsanity.com/paper/1704.08082/) (2017) - [Rethinking Evaluation in ASR: Are Our Models Robust Enough?](https://mlsanity.com/paper/2010.11745/) (2020) - [Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation](https://mlsanity.com/paper/2106.14999/) (2021) - [Unsupervised Domain Adaptation using Feature-Whitening and Consensus Loss](https://mlsanity.com/paper/1903.03215/) (2019) - [SITA: Single Image Test-time Adaptation](https://mlsanity.com/paper/2112.02355/) (2021) - [Test-time Batch Statistics Calibration for Covariate Shift](https://mlsanity.com/paper/2110.04065/) (2021) - [MixNorm: Test-Time Adaptation Through Online Normalization Estimation](https://mlsanity.com/paper/2110.11478/) (2021) - [Domain Adversarial Training for Accented Speech Recognition](https://mlsanity.com/paper/1806.02786/) (2018) - [Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training](https://mlsanity.com/paper/2011.13439/) (2020) - [Large-Scale Domain Adaptation via Teacher-Student Learning](https://mlsanity.com/paper/1708.05466/) (2017) - [Test time Adaptation through Perturbation Robustness](https://mlsanity.com/paper/2110.10232/) (2021) - [The RWTH ASR System for TED-LIUM Release 2: Improving Hybrid HMM with SpecAugment](https://mlsanity.com/paper/2004.00960/) (2020) ## Built on by (most cited first, 19 of 19) - [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023) - [E-BATS: Efficient Backpropagation-Free Test-Time Adaptation for Speech Foundation Models](https://mlsanity.com/paper/2506.07078/) (2025) - [REALM: Robust Entropy Adaptive Loss Minimization for Improved Single-Sample Test-Time Adaptation](https://mlsanity.com/paper/2309.03964/) (2023) - [Test-Time Training for Speech](https://mlsanity.com/paper/2309.10930/) (2023) - [SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech Recognition](https://mlsanity.com/paper/2409.10429/) (2024) - [LI-TTA: Language Informed Test-Time Adaptation for Automatic Speech Recognition](https://mlsanity.com/paper/2408.05769/) (2024) - [Whisper-CD: Accurate Long-Form Speech Recognition using Multi-Negative Contrastive Decoding](https://mlsanity.com/paper/2603.06193/) (2026) - [Recent Trends in Distant Conversational Speech Recognition: A Review of CHiME-7 and 8 DASR Challenges](https://mlsanity.com/paper/2507.18161/) (2025) - [Test-Time Training for Speech Enhancement](https://mlsanity.com/paper/2508.01847/) (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) - [Self-Train Before You Transcribe](https://mlsanity.com/paper/2406.12937/) (2024) - [Examining Test-Time Adaptation for Personalized Child Speech Recognition](https://mlsanity.com/paper/2409.13095/) (2024) - [Robust Unsupervised Adaptation of a Speech Recogniser Using Entropy Minimisation and Speaker Codes](https://mlsanity.com/paper/2506.10653/) (2025) - [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) - [Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models](https://mlsanity.com/paper/2605.08186/) (2026) - [Robust Multi-Tier Infant-Centered Audio Understanding with Whisper via Structured Speaker Conditioning](https://mlsanity.com/paper/2608.11587/) (2026) - [Test-time adaptation for speech enhancement with an autoregressive speech prior](https://mlsanity.com/paper/2609.03622/) (2026) ## Abstract (arXiv) Although deep learning-based end-to-end Automatic Speech Recognition (ASR) has shown remarkable performance in recent years, it suffers severe performance regression on test samples drawn from different data distributions. Test-time Adaptation (TTA), previously explored in the computer vision area, aims to adapt the model trained on source domains to yield better predictions for test samples, often out-of-domain, without accessing the source data. Here, we propose the Single-Utterance Test-time Adaptation (SUTA) framework for ASR, which is the first TTA study on ASR to our best knowledge. The single-utterance TTA is a more realistic setting that does not assume test data are sampled from identical distribution and does not delay on-demand inference due to pre-collection for the batch of adaptation data. SUTA consists of unsupervised objectives with an efficient adaptation strategy. Empirical results demonstrate that SUTA effectively improves the performance of the source ASR model evaluated on multiple out-of-domain target corpora and in-domain test samples.