TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

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

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
Otsikko2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)
KustantajaIEEE
ISBN (elektroninen)978-1-7281-1123-0
ISBN (painettu)978-1-7281-1124-7
DOI - pysyväislinkit
TilaJulkaistu - 22 lokakuuta 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaIEEE Workshop on Applications of Signal Processing to Audio and Acoustics -
Kesto: 1 tammikuuta 1900 → …

Julkaisusarja

NimiIEEE Workshop on Applications of Signal Processing to Audio and Acoustics
ISSN (painettu)1931-1168
ISSN (elektroninen)1947-1629

Conference

ConferenceIEEE Workshop on Applications of Signal Processing to Audio and Acoustics
Ajanjakso1/01/00 → …

Tiivistelmä

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.

Tutkimusalat

Julkaisufoorumi-taso