面向无源跨语料库语音情感识别的情感感知对比适应网络
Emotion-Aware Contrastive Adaptation Network for Source-Free Cross-Corpus Speech Emotion Recognition
AI总结：
针对无源跨语料库SER中无法访问源数据的问题，本文提出ECAN，结合最近邻对比学习与监督对比学习实现局部一致性和类别级适应，并在多个语料库上显著优于现有方法。
摘要：
跨语料库语音情感识别（SER）旨在将来自带标签源语料库的情感知识迁移到无标签语料库。然而，以往方法在适应过程中需要访问源数据，而由于数据隐私保护方面的顾虑，这在现实场景中是无法实现的。本文解决一个更具实用性的任务，即无源跨语料库SER，其中预训练的源模型在无法访问源数据的情况下适应目标领域。为解决该问题，我们提出了一种名为情感感知对比适应网络（ECAN）的新方法。其核心思想是在考虑全局类别级适应的同时，捕获样本之间的局部邻域信息。具体而言，我们提出最近邻对比学习，以促进高度相似样本的特征之间的局部情感一致性。此外，仅依赖最近邻可能导致聚类之间的边界模糊。因此，我们引入监督对比学习，以促使代表不同情感的聚类之间实现更大程度的分离，从而促进更好的类别级适应。大量实验表明，在若干语音情感语料库上的无源跨语料库SER设置下，我们提出的ECAN显著优于最先进方法。
英文摘要：
Cross-corpus speech emotion recognition (SER) aims to transfer emotional knowledge from a labeled source corpus to an unlabeled corpus. However, prior methods require access to source data during adaptation, which is unattainable in real-life scenarios due to data privacy protection concerns. This paper tackles a more practical task, namely source-free cross-corpus SER, where a pre-trained source model is adapted to the target domain without access to source data. To address the problem, we propose a novel method called emotion-aware contrastive adaptation network (ECAN). The core idea is to capture local neighborhood information between samples while considering the global class-level adaptation. Specifically, we propose a nearest neighbor contrastive learning to promote local emotion consistency among features of highly similar samples. Furthermore, relying solely on nearest neighborhoods may lead to ambiguous boundaries between clusters. Thus, we incorporate supervised contrastive learning to encourage greater separation between clusters representing different emotions, thereby facilitating improved class-level adaptation. Extensive experiments indicate that our proposed ECAN significantly outperforms state-of-the-art methods under the source-free cross-corpus SER setting on several speech emotion corpora.
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。
