Adversarial Domain Adaptation for Open Set Acoustic Scene Classification

Chunxia Ren, Shengchen Li*

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review


Many algorithms classify acoustic scenes with predefined acoustic scenes categories but few addresses identifying acoustic scenes that are not predefined (usually referred as “unknown acoustic scenes”), which is known as “open set” problem for acoustic scene classification. Traditional methods generally use a “one-size-fits-all” threshold to make a second judgment on the output of trained model. The boundary between known and unknown scenes cannot be learned. To enable this boundary to be programmed, this paper proposes a novel method to introduce adversarial domain adaptation into the open set acoustic scene classification. In this method, known scenes are classified through the adaptation of target domain and source domain, and unknown scenes are distinguished by adversarial training with the help of preset pseudo-threshold. Not only the discrimination between unknown classes and known classes can be learned during the adversarial training process, but the overall performance of the open set acoustic scene classification algorithm is also improved. The proposed system achieves better performance compared with the baseline of open set acoustic scene detection in Detection and Classification on Acoustic Scenes and Events challenge 2019.

Original languageEnglish
Title of host publicationProceedings of the 8th Conference on Sound and Music Technology - Selected Papers from CSMT
EditorsXi Shao, Kun Qian, Li Zhou, Xin Wang, Ziping Zhao
PublisherSpringer Science and Business Media Deutschland GmbH
Number of pages12
ISBN (Print)9789811616488
Publication statusPublished - 2021
Event8th Conference on Sound and Music Technology, CSMT 2020 - Taiyuan, China
Duration: 5 Nov 20208 Nov 2020

Publication series

NameLecture Notes in Electrical Engineering
Volume761 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119


Conference8th Conference on Sound and Music Technology, CSMT 2020


  • Acoustic scene classification
  • Adversarial domain adaptation
  • Open set
  • Pseudo-threshold

Cite this