发表机构
School of Computing and Electrical Engineering; Indian Institute of Technology Mandi（计算与电气工程学院; 曼迪印度理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究在声学场景分类中基于CNN和Transformer特征表示时域适应技术的有效性，评估DANN和CDAN两种技术，发现DANN对两种特征提取器有效，CDAN仅对基于CNN的有效，为定制域适应方法提供见解，实验评估支持该结论。
AI 中文摘要
本文探讨了在基于卷积神经网络（CNN）和基于Transformer的特征表示进行声学场景分类时，域适应技术的有效性。评估了两种著名的域适应技术，即域对抗神经网络（DANN）和条件域对抗网络（CDAN）在各种域偏移下的性能。研究表明，DANN对两种特征提取器都能相当一致地提供有效的域适应，而CDAN仅对基于CNN的特征提取器有效。该研究为如何根据底层特征表示定制域适应方法提供了见解。在DCASE 2020数据集上使用多个设备进行的实验评估支持了这些观察结果。
英文摘要
This paper explores the effectiveness of domain adaptation techniques when using convolutional neural network (CNN)-based and transformer-based feature representations for acoustic scene classification. Two well-known domain adaptation techniques, namely domain adversarial neural network (also called DANN) and conditional domain adversarial network (also called CDAN) are evaluated under various domain shifts. Our study indicates that DANN provides effective domain adaptation fairly consistently for both feature extractors. On the other hand, CDAN provides effective domain adaptation only for CNN-based feature extractors. The study gives insights into how domain adaptation methods may need to be tailored to the underlying feature representation. Experimental evaluation with multiple devices on the DCASE 2020 dataset supports the observations.
Comments6 pages , 5 figures
