TY - GEN
T1 - Two-Stage Classification Learning for Open Set Acoustic Scene Classification
AU - Ren, Chunxia
AU - Li, Shengchen
N1 - Publisher Copyright:
© 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
PY - 2021
Y1 - 2021
N2 - Most of the research on acoustic scene classification (ASC) focuses on classification problem with only known scene classes. In practice, scene classification problem to be solved generally is based on an open set, which contains unknown scenes. This paper proposes a two-stage method that solves the open set problem on ASC. The proposed system decomposes open set ASC problem into two stages. To mitigate the impact of unknown scenes on the subsequent recognition process of known scenes, the first stage is to identify unknown scenes. The second stage classifies defined acoustic scenes. In this case, the threshold selection strategy we proposed further sorts out unknown scenes that were not identified in the previous stage. Experiments show that the method proposed in this paper can effectively identify unknown scenes and classify known scenes, by segmenting the open set acoustic scene classification task and selecting an appropriate judgment threshold. On the development dataset released by DCASE Challenge 2019 Task 1C, the model proposed outperforms the first place.
AB - Most of the research on acoustic scene classification (ASC) focuses on classification problem with only known scene classes. In practice, scene classification problem to be solved generally is based on an open set, which contains unknown scenes. This paper proposes a two-stage method that solves the open set problem on ASC. The proposed system decomposes open set ASC problem into two stages. To mitigate the impact of unknown scenes on the subsequent recognition process of known scenes, the first stage is to identify unknown scenes. The second stage classifies defined acoustic scenes. In this case, the threshold selection strategy we proposed further sorts out unknown scenes that were not identified in the previous stage. Experiments show that the method proposed in this paper can effectively identify unknown scenes and classify known scenes, by segmenting the open set acoustic scene classification task and selecting an appropriate judgment threshold. On the development dataset released by DCASE Challenge 2019 Task 1C, the model proposed outperforms the first place.
KW - Acoustic scene classification
KW - Open set
KW - Threshold selection strategy
KW - Two-stage classification
UR - http://www.scopus.com/inward/record.url?scp=85105883775&partnerID=8YFLogxK
U2 - 10.1007/978-981-16-1649-5_11
DO - 10.1007/978-981-16-1649-5_11
M3 - Conference Proceeding
AN - SCOPUS:85105883775
SN - 9789811616488
T3 - Lecture Notes in Electrical Engineering
SP - 124
EP - 133
BT - Proceedings of the 8th Conference on Sound and Music Technology - Selected Papers from CSMT
A2 - Shao, Xi
A2 - Qian, Kun
A2 - Zhou, Li
A2 - Wang, Xin
A2 - Zhao, Ziping
PB - Springer Science and Business Media Deutschland GmbH
T2 - 8th Conference on Sound and Music Technology, CSMT 2020
Y2 - 5 November 2020 through 8 November 2020
ER -