Unsupervised Adversarial Domain Adaptation Based on The Wasserstein Distance For Acoustic Scene Classification
Unsupervised Adversarial Domain Adaptation Based on The Wasserstein Distance For Acoustic Scene Classification
复制标题
DOI：
10.1109/waspaa.2019.8937231
复制
发表时间：
2019-04
期刊：
影响因子：
--
通讯作者：
K. Drossos;P. Magron;T. Virtanen
中科院分区：
文献类型：
--
作者：
K. Drossos;P. Magron;T. Virtanen
在基于深度学习的机器听力领域，一个具有挑战性的问题是，当使用来自未知条件的数据时，性能会下降。在本文中，我们专注于声学场景分类（ASC）任务，并提出了一种对抗性深度学习方法，允许调整声学场景分类系统来处理由不同记录设备捕获的数据产生的新声学通道。本文在基于h - Δ h -distance的理论模型和前人针对ASC无监督域自适应的对抗性判别深度学习方法的基础上，提出了一种基于Wasserstein距离的对抗性训练方法。我们使用TUT声学场景数据集，将未见条件下数据的最先进平均精度从32%提高到45%。
A challenging problem in deep learning-based machine listening field is the degradation of the performance when using data from unseen conditions. In this paper we focus on the acoustic scene classification (ASC) task and propose an adversarial deep learning method to allow adapting an acoustic scene classification system to deal with a new acoustic channel resulting from data captured with a different recording device. We build upon the theoretical model of ℋΔℋ-distance and previous adversarial discriminative deep learning method for ASC unsupervised domain adaptation, and we present an adversarial training based method using the Wasserstein distance. We improve the state-of-the-art mean accuracy on the data from the unseen conditions from 32% to 45%, using the TUT Acoustic Scenes dataset.