E-BATS: Efficient Backpropagation-Free Test-Time Adaptation for Speech Foundation Models

• URL: http://arxiv.org/abs/2506.07078v1
• Date: Sun, 08 Jun 2025 10:33:37 GMT
• Title: E-BATS: Efficient Backpropagation-Free Test-Time Adaptation for Speech Foundation Models
• Authors: Jiaheng Dong, Hong Jia, Soumyajit Chatterjee, Abhirup Ghosh, James Bailey, Ting Dang,
• Abstract summary: Speech Foundation Models encounter significant performance degradation when deployed in real-world scenarios involving acoustic domain shifts.<n>Test-time adaptation (TTA) has emerged as a viable strategy to address such domain shifts at inference time without requiring access to source data or labels.<n>E-BATS is the first Efficient BAckpropagation-free TTA framework designed explicitly for speech foundation models.
• Score: 11.696474872520808
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Speech Foundation Models encounter significant performance degradation when deployed in real-world scenarios involving acoustic domain shifts, such as background noise and speaker accents. Test-time adaptation (TTA) has recently emerged as a viable strategy to address such domain shifts at inference time without requiring access to source data or labels. However, existing TTA approaches, particularly those relying on backpropagation, are memory-intensive, limiting their applicability in speech tasks and resource-constrained settings. Although backpropagation-free methods offer improved efficiency, existing ones exhibit poor accuracy. This is because they are predominantly developed for vision tasks, which fundamentally differ from speech task formulations, noise characteristics, and model architecture, posing unique transferability challenges. In this paper, we introduce E-BATS, the first Efficient BAckpropagation-free TTA framework designed explicitly for speech foundation models. E-BATS achieves a balance between adaptation effectiveness and memory efficiency through three key components: (i) lightweight prompt adaptation for a forward-pass-based feature alignment, (ii) a multi-scale loss to capture both global (utterance-level) and local distribution shifts (token-level) and (iii) a test-time exponential moving average mechanism for stable adaptation across utterances. Experiments conducted on four noisy speech datasets spanning sixteen acoustic conditions demonstrate consistent improvements, with 4.1%-13.5% accuracy gains over backpropagation-free baselines and 2.0-6.4 times GPU memory savings compared to backpropagation-based methods. By enabling scalable and robust adaptation under acoustic variability, this work paves the way for developing more efficient adaptation approaches for practical speech processing systems in real-world environments.

Related papers

• Test-Time Training for Speech Enhancement [2.9598903898834497]
  This paper introduces a novel application of Test-Time Training (TTT) for Speech Enhancement.<n>It addresses the challenges posed by unpredictable noise conditions and domain shifts.<n>We show consistent improvements across speech quality metrics, outperforming the baseline model.
  arXiv  Detail & Related papers  (2025-08-03T17:02:55Z)
• Reliable Few-shot Learning under Dual Noises [166.53173694689693]
  We propose DEnoised Task Adaptation (DETA++) for reliable few-shot learning.<n>DETA++ employs a memory bank to store and refine clean regions for each inner-task class, based on which a Local Nearestid (LocalNCC) is devised to yield noise-robust predictions on query samples.<n>Extensive experiments demonstrate the effectiveness and flexibility of DETA++.
  arXiv  Detail & Related papers  (2025-06-19T14:05:57Z)
• Adaptive Noise Resilient Keyword Spotting Using One-Shot Learning [5.967661928760498]
  Keywords spotting (KWS) is a key component of smart devices, enabling efficient and intuitive audio interaction.<n> KWS systems often suffer performance degradation under real-world operating conditions.<n>This study proposes a low computational approach for continuous noise adaptation of pretrained neural networks used for KWS classification.
  arXiv  Detail & Related papers  (2025-05-14T11:39:47Z)
• Homogeneous Speaker Features for On-the-Fly Dysarthric and Elderly Speaker Adaptation [71.31331402404662]
  This paper proposes two novel data-efficient methods to learn dysarthric and elderly speaker-level features. Speaker-regularized spectral basis embedding-SBE features that exploit a special regularization term to enforce homogeneity of speaker features in adaptation. Feature-based learning hidden unit contributions (f-LHUC) that are conditioned on VR-LH features that are shown to be insensitive to speaker-level data quantity in testtime adaptation.
  arXiv  Detail & Related papers  (2024-07-08T18:20:24Z)
• Advancing Test-Time Adaptation in Wild Acoustic Test Settings [26.05732574338255]
  Speech signals follow short-term consistency, requiring specialized adaptation strategies. We propose a novel wild acoustic TTA method tailored for ASR fine-tuned acoustic foundation models. Our approach outperforms existing baselines under various wild acoustic test settings.
  arXiv  Detail & Related papers  (2023-10-14T06:22:08Z)
• DDTSE: Discriminative Diffusion Model for Target Speech Extraction [62.422291953387955]
  We introduce the Discriminative Diffusion model for Target Speech Extraction (DDTSE) We apply the same forward process as diffusion models and utilize the reconstruction loss similar to discriminative methods. We devise a two-stage training strategy to emulate the inference process during model training.
  arXiv  Detail & Related papers  (2023-09-25T04:58:38Z)
• Factorised Speaker-environment Adaptive Training of Conformer Speech Recognition Systems [31.813788489512394]
  This paper proposes a novel factorised speaker-environment adaptive training and test time adaptation approach for Conformer ASR models. Experiments on the 300-hr WHAM noise corrupted Switchboard data suggest that factorised adaptation consistently outperforms the baseline. Further analysis shows the proposed method offers potential for rapid adaption to unseen speaker-environment conditions.
  arXiv  Detail & Related papers  (2023-06-26T11:32:05Z)
• Parameter-Efficient Learning for Text-to-Speech Accent Adaptation [58.356667204518985]
  This paper presents a parameter-efficient learning (PEL) to develop a low-resource accent adaptation for text-to-speech (TTS) A resource-efficient adaptation from a frozen pre-trained TTS model is developed by using only 1.2% to 0.8% of original trainable parameters. Experiment results show that the proposed methods can achieve competitive naturalness with parameter-efficient decoder fine-tuning.
  arXiv  Detail & Related papers  (2023-05-18T22:02:59Z)
• Multi-source Domain Adaptation for Text-independent Forensic Speaker Recognition [36.83842373791537]
  Adapting speaker recognition systems to new environments is a widely-used technique to improve a well-performing model. Previous studies focus on single domain adaptation, which neglects a more practical scenario where training data are collected from multiple acoustic domains. Three novel adaptation methods are proposed to further promote adaptation performance across multiple acoustic domains.
  arXiv  Detail & Related papers  (2022-11-17T22:11:25Z)
• On-the-Fly Feature Based Rapid Speaker Adaptation for Dysarthric and Elderly Speech Recognition [53.17176024917725]
  Scarcity of speaker-level data limits the practical use of data-intensive model based speaker adaptation methods. This paper proposes two novel forms of data-efficient, feature-based on-the-fly speaker adaptation methods.
  arXiv  Detail & Related papers  (2022-03-28T09:12:24Z)
• Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition [65.84978547406753]
  Test-time Adaptation aims to adapt the model trained on source domains to yield better predictions for test samples. Single-Utterance Test-time Adaptation (SUTA) is the first TTA study in speech area to our best knowledge.
  arXiv  Detail & Related papers  (2022-03-27T06:38:39Z)
• Bayesian Learning for Deep Neural Network Adaptation [57.70991105736059]
  A key task for speech recognition systems is to reduce the mismatch between training and evaluation data that is often attributable to speaker differences. Model-based speaker adaptation approaches often require sufficient amounts of target speaker data to ensure robustness. This paper proposes a full Bayesian learning based DNN speaker adaptation framework to model speaker-dependent (SD) parameter uncertainty.
  arXiv  Detail & Related papers  (2020-12-14T12:30:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.