Skip to Main content Skip to Navigation
Conference papers

Unsupervised Adversarial Domain Adaptation Based On The Wasserstein Distance For Acoustic Scene Classification

Konstantinos Drossos 1 Paul Magron 2, 1 Tuomas Virtanen 1
2 IRIT-SC - Signal et Communications
IRIT - Institut de recherche en informatique de Toulouse
Abstract : 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 H{\Delta}H-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.
Complete list of metadata

https://hal.inria.fr/hal-03132097
Contributor : Paul Magron Connect in order to contact the contributor
Submitted on : Thursday, February 4, 2021 - 6:08:11 PM
Last modification on : Wednesday, November 3, 2021 - 6:50:36 AM

Links full text

Identifiers

Citation

Konstantinos Drossos, Paul Magron, Tuomas Virtanen. Unsupervised Adversarial Domain Adaptation Based On The Wasserstein Distance For Acoustic Scene Classification. IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA 2019), Oct 2019, New Paltz (NY), United States. ⟨10.1109/WASPAA.2019.8937231⟩. ⟨hal-03132097⟩

Share

Metrics

Les métriques sont temporairement indisponibles