BLINC：用于免训练语音增强自适应的盲校准
BLINC: Blind Calibration For Training-Free Speech Enhancement Adaptation
- University of Stuttgart（斯图加特大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
BLINC提出免训练的测试时自适应方法，通过直方图匹配将预测掩码重映射到盲特征参数化的双峰分布，提升语音增强模型在域偏移下的性能，无需反向传播且开销极小。
AI中文摘要：
语音增强（SE）模型在域偏移下性能会下降，因此在部署期间必须适应未见过的目标域。现有的多数用于SE的测试时自适应（TTA）方法通过使用自监督损失调整模型权重的一个子集来实现自适应，这需要在测试时进行反向传播，并永久性地改变模型。我们转而重新校准预测本身，并提出了BLINC，一种免训练的TTA方法，通过直方图匹配将预测的时频掩码重新映射到双峰目标分布上。在测试时，目标分布由含噪录音的盲特征参数化，因此既不涉及经典算法的参考分布，也不涉及在线度量优化。BLINC在几乎所有目标条件下都提升了两个被评估SE模型的整体质量，并以最小的开销达到或超过了基于损失的TTA基线。
英文摘要：
Speech enhancement (SE) models degrade under domain shifts and have to adapt to unseen target domains during deployment. Most existing test-time adaptation (TTA) methods for SE do so by adapting a subset of the model weights using a self-supervised loss, which requires backpropagation at test-time and permanently alters the model. We instead recalibrate the prediction itself and propose BLINC, a training-free TTA method that remaps the predicted time-frequency mask onto a bimodal target distribution by histogram matching. At test-time, the target distribution is parameterized from blind features of the noisy recording, so neither a reference distribution from a classical algorithm nor online metric optimization is involved. BLINC improves the overall quality of both evaluated SE models on almost every target condition and matches or exceeds the loss-based TTA baselines at minimal overhead.
