Adversarial Domain Adaptation with Paired Examples for Acoustic Scene Classification on Different Recording Devices

TL;DR

This paper explores adversarial domain adaptation techniques, especially cycle GANs, to improve acoustic scene classification across different recording devices using paired data, achieving significant accuracy gains and reduced training costs.

Contribution

It demonstrates that cycle GANs leveraging paired examples significantly enhance domain adaptation performance in acoustic scene classification.

Findings

Cycle GAN achieves 66% relative accuracy improvement on target devices.

Paired data improves accuracy over unpaired data.

Using paired data reduces training computational costs.

Abstract

In classification tasks, the classification accuracy diminishes when the data is gathered in different domains. To address this problem, in this paper, we investigate several adversarial models for domain adaptation (DA) and their effect on the acoustic scene classification task. The studied models include several types of generative adversarial networks (GAN), with different loss functions, and the so-called cycle GAN which consists of two interconnected GAN models. The experiments are performed on the DCASE20 challenge task 1A dataset, in which we can leverage the paired examples of data recorded using different devices, i.e., the source and target domain recordings. The results of performed experiments indicate that the best performing domain adaptation can be obtained using the cycle GAN, which achieves as much as 66% relative improvement in accuracy for the target domain device, while only 6\% relative decrease in accuracy on the source domain. In addition, by utilizing the paired data examples, we are able to improve the overall accuracy over the model trained using larger unpaired data set, while decreasing the computational cost of the model training.