SS-SLA-2: Advanced Topics on Sound Event and Scene Analysis
Thu, 16 Dec, 14:00 - 16:00 Japan Standard Time (UTC +9)
Thu, 16 Dec, 05:00 - 07:00 Coordinated Universal Time
Thu, 16 Dec, 00:00 - 02:00 Eastern Standard Time (UTC -5)
Wed, 15 Dec, 21:00 - 23:00 Pacific Standard Time (UTC -8)
Session Co-Chairs: Keisuke Imoto, Doshisha University and Tatsuya Komatsu, Line corporation
Track: Speech, Language, and Audio (SLA)

SS-SLA-2.1: COMPARISON OF LOW COMPLEXITY SELF-ATTENTION MECHANISMS FOR ACOUSTIC EVENT DETECTION
Tatsuya Komatsu, Robin Scheibler, LINE Corporation, Japan

SS-SLA-2.2: DUAL-PATH TRANSFORMER FOR MACHINE CONDITION MONITORING
Jisheng Bai, Mou Wang, Jianfeng Chen, School of Marine Science and Technology, Northwestern Polytechnical University, China

SS-SLA-2.3: SPEAKER COUNT: A NEW BUILDING BLOCK FOR SPEAKER DIARIZATION
Thanh Thi-Hien Duong, Hanoi University of Mining and Geology, Viet Nam; Phi-Le Nguyen, Hanoi University of Science and Technology, Viet Nam; Duc-Chien Nguyen, Hong-Son Nguyen, Aimenext Join Stock Company, Viet Nam; Huy Phan, Queen Mary University of London, United Kingdom of Great Britain and Northern Ireland; Ngoc Q. K. Duong, InterDigital, France

SS-SLA-2.4: Multitask Learning of Acoustic Scenes and Events Using Dynamic Weight Adaptation Based on Multi-Focal Loss
Kayo Nada, Keisuke Imoto, Reina Iwamae, Takao Tsuchiya, Doshisha University, Japan

SS-SLA-2.5: INVESTIGATION ON SPATIAL AND FREQUENCY-BASED FEATURES FOR ASYNCHRONOUS ACOUSTIC SCENE ANALYSIS
Yuki Shiroma, Sayaka Shiota, Nobutaka Ono, Hitoshi Kiya, Tokyo Metropolitan University, Japan; Keisuke Imoto, Doshisha University, Japan

SS-SLA-2.6: Analysis on Roles of DNNs in End-to-End Acoustic Scene Analysis Framework with Distributed Sound-to-Light Conversion Devices
Yuma Kinoshita, Nobutaka Ono, Tokyo Metropolitan University, Japan