# Advancing Test-Time Adaptation in Wild Acoustic Test Settings

arXiv: https://arxiv.org/abs/2310.09505 · HTML: https://mlsanity.com/paper/2310.09505/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 14 Oct 2023.

## Builds on (most cited first, 28 of 28)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation](https://mlsanity.com/paper/2208.05117/) (2022)
- [Voice2Series: Reprogramming Acoustic Models for Time Series Classification](https://mlsanity.com/paper/2106.09296/) (2021)
- [CTC-Segmentation of Large Corpora for German End-to-end Speech Recognition](https://mlsanity.com/paper/2007.09127/) (2020)
- [A scalable noisy speech dataset and online subjective test framework](https://mlsanity.com/paper/1909.08050/) (2019)
- [Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognition](https://mlsanity.com/paper/2109.01163/) (2021)
- [Learning Hidden Unit Contributions for Unsupervised Acoustic Model Adaptation](https://mlsanity.com/paper/1601.02828/) (2016)
- [Domain Adversarial Training for Accented Speech Recognition](https://mlsanity.com/paper/1806.02786/) (2018)
- [Large-Scale Domain Adaptation via Teacher-Student Learning](https://mlsanity.com/paper/1708.05466/) (2017)
- [Unsupervised Domain Adaptation for Robust Speech Recognition via Variational Autoencoder-Based Data Augmentation](https://mlsanity.com/paper/1707.06265/) (2017)
- [From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition](https://mlsanity.com/paper/2301.07851/) (2023)
- [End-to-End Automatic Speech Recognition Integrated With CTC-Based Voice Activity Detection](https://mlsanity.com/paper/2002.00551/) (2020)
- [Temporal Coherent Test-Time Optimization for Robust Video Classification](https://mlsanity.com/paper/2302.14309/) (2023)
- [Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching](https://mlsanity.com/paper/2104.07491/) (2021)
- [Blank-regularized CTC for Frame Skipping in Neural Transducer](https://mlsanity.com/paper/2305.11558/) (2023)
- [Confidence Score Based Conformer Speaker Adaptation for Speech Recognition](https://mlsanity.com/paper/2206.12045/) (2022)
- [STRODE: Stochastic Boundary Ordinary Differential Equation](https://mlsanity.com/paper/2107.08273/) (2021)
- [Parameter-Efficient Learning for Text-to-Speech Accent Adaptation](https://mlsanity.com/paper/2305.11320/) (2023)

## Built on by (most cited first, 7 of 7)

- [E-BATS: Efficient Backpropagation-Free Test-Time Adaptation for Speech Foundation Models](https://mlsanity.com/paper/2506.07078/) (2025)
- [Histogram-based Parameter-efficient Tuning for Passive and Active Sonar Classification](https://mlsanity.com/paper/2504.15214/) (2025)
- [SUTA-LM: Bridging Test-Time Adaptation and Language Model Rescoring for Robust ASR](https://mlsanity.com/paper/2506.11121/) (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)
- [Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models](https://mlsanity.com/paper/2605.08186/) (2026)
- [Drift-Augmented Scoring: Text-Derived Noise Robustness for Zero-Shot Audio-Language Classification](https://mlsanity.com/paper/2606.04844/) (2026)

## Abstract (arXiv)

Acoustic foundation models, fine-tuned for Automatic Speech Recognition (ASR), suffer from performance degradation in wild acoustic test settings when deployed in real-world scenarios. Stabilizing online Test-Time Adaptation (TTA) under these conditions remains an open and unexplored question. Existing wild vision TTA methods often fail to handle speech data effectively due to the unique characteristics of high-entropy speech frames, which are unreliably filtered out even when containing crucial semantic content. Furthermore, unlike static vision data, speech signals follow short-term consistency, requiring specialized adaptation strategies. In this work, we propose a novel wild acoustic TTA method tailored for ASR fine-tuned acoustic foundation models. Our method, Confidence-Enhanced Adaptation, performs frame-level adaptation using a confidence-aware weight scheme to avoid filtering out essential information in high-entropy frames. Additionally, we apply consistency regularization during test-time optimization to leverage the inherent short-term consistency of speech signals. Our experiments on both synthetic and real-world datasets demonstrate that our approach outperforms existing baselines under various wild acoustic test settings, including Gaussian noise, environmental sounds, accent variations, and sung speech.