语音情感识别中的测试时适应
Test-Time Adaptation for Speech Emotion Recognition
AI总结：
本文研究了语音情感识别中测试时适应方法的有效性，评估了11种方法，发现无需反向传播的TTA方法表现最佳，而其他方法因假设不成立而效果不佳。
摘要：
语音情感识别（SER）系统的实际应用受到其对领域偏移的脆弱性影响，例如说话人变化、表演与自然情感的区别以及跨语料库的差异。尽管领域适应和微调已被广泛研究，但它们需要源数据或标记的目标数据，这些数据通常不可用或在SER中引发隐私问题。测试时适应（TTA）通过在推理时仅使用未标记的目标数据来调整模型，从而填补了这一空白。然而，TTA主要为图像分类和语音识别设计，其在缓解SER中独特的领域偏移方面的有效性尚未被研究。在本文中，我们首次系统地评估和比较了11种TTA方法，覆盖三个代表性SER任务。结果表明，无需反向传播的TTA方法是最有前途的。相反，熵最小化和伪标签法通常失败，因为它们的核心假设是单一的、自信的地面真相标签，这与情感表达的固有模糊性不兼容。此外，没有单一方法在所有情况下都表现出色，其有效性高度依赖于分布偏移和任务。
英文摘要：
The practical utility of Speech Emotion Recognition (SER) systems is undermined by their fragility to domain shifts, such as speaker variability, the distinction between acted and naturalistic emotions, and cross-corpus variations. While domain adaptation and fine-tuning are widely studied, they require either source data or labelled target data, which are often unavailable or raise privacy concerns in SER. Test-time adaptation (TTA) bridges this gap by adapting models at inference using only unlabeled target data. Yet, having been predominantly designed for image classification and speech recognition, the efficacy of TTA for mitigating the unique domain shifts in SER has not been investigated. In this paper, we present the first systematic evaluation and comparison covering 11 TTA methods across three representative SER tasks. The results indicate that backpropagation-free TTA methods are the most promising. Conversely, entropy minimization and pseudo-labeling generally fail, as their core assumption of a single, confident ground-truth label is incompatible with the inherent ambiguity of emotional expression. Further, no single method universally excels, and its effectiveness is highly dependent on the distributional shifts and tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
