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

TL;DR

E-BATS introduces an efficient, backpropagation-free test-time adaptation framework for speech models, significantly improving accuracy and reducing memory usage in noisy, real-world acoustic conditions.

Contribution

It is the first to tailor backpropagation-free TTA specifically for speech models, combining lightweight prompts, multi-scale loss, and stable adaptation mechanisms.

Findings

Achieves 4.1%-13.5% accuracy improvements over baselines.

Saves 2.0-6.4 times GPU memory compared to backpropagation methods.

Demonstrates robustness across diverse noisy speech datasets.

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.