It is well known that the mismatch between training (source) and test (target) data distribution will significantly decrease the performance of acoustic scene classification (ASC) systems. To address this issue, domain adaptation (DA) is one solution and many unsupervised DA methods have been proposed. These methods focus on a scenario of single source domain to single target domain. However, we will face such problem that test data comes from multiple target domains. This problem can be addressed by producing one model per target domain, but this solution is too costly. In this paper, we propose a novel unsupervised multi-target domain adaption (MTDA) method for ASC, which can adapt to multiple target domains simultaneously and make use of the underlying relation among multiple domains. Specifically, our approach combines traditional adversarial adaptation with two novel discriminator tasks that learns a common subspace shared by all domains. Furthermore, we propose to divide the target domain into the easy-to-adapt and hard-to-adapt domain, which enables the system to pay more attention to hard-to-adapt domain in training. The experimental results on the DCASE 2020 Task 1-A dataset and the DCASE 2019 Task 1-B dataset show that our proposed method significantly outperforms the previous unsupervised DA methods.
翻译:众所周知,培训(源)和测试(目标)数据分布之间的不匹配将大大降低声场分类(ASC)系统的性能。为解决这一问题,域适应(DA)是一个解决办法,提出了许多未受监督的DA方法。这些方法侧重于单一源域的设想,将单一目标域改为单一目标域。然而,我们将面临测试数据来自多个目标域的问题。可以通过每个目标域生成一个模型来解决这个问题,但这一解决方案成本太高。在本文件中,我们提议为ASC采用新的、不受监督的多目标域调整(MTDA)方法,该方法可以同时适应多个目标域,并利用多个域之间的内在关系。具体地说,我们的方法将传统的对抗性适应与两个新颖的区分任务结合起来,即学习所有域共享的共同子空间。此外,我们提议将目标域分为一个容易适应和难以适应域域,使系统能够在培训中更多地注意硬到适应域域。在DCASE 2020 任务1-A A A 任务 1-A A 和 DASA 任务 1 显示我们先前的DAS 1-A 1 格式上的拟议数据系统 显示未显示前的DASASASE 1 任务 2019 。