AUD-27.2
CNN-TRANSFORMER WITH SELF-ATTENTION NETWORK FOR SOUND EVENT DETECTION
Keigo Wakayama, Shoichiro Saito, NTT Corporation, Japan
Session:
Detection and Classification of Acoustic Scenes and Events VI: Events
Track:
Audio and Acoustic Signal Processing
Location:
Gather Area K
Presentation Time:
Thu, 12 May, 21:00 - 21:45 China Time (UTC +8)
Thu, 12 May, 13:00 - 13:45 UTC
Thu, 12 May, 13:00 - 13:45 UTC
Session Chair:
Dimitra Emmanouilidou, Microsoft Corporation
Session AUD-27
AUD-27.1: SOUND EVENT DETECTION GUIDED BY SEMANTIC CONTEXTS OF SCENES
Noriyuki Tonami, Ryotaro Nagase, Yuki Okamoto, Takahiro Fukumori, Yoichi Yamashita, Ritsumeikan University, Japan; Keisuke Imoto, Doshisha University, Japan
AUD-27.2: CNN-TRANSFORMER WITH SELF-ATTENTION NETWORK FOR SOUND EVENT DETECTION
Keigo Wakayama, Shoichiro Saito, NTT Corporation, Japan
AUD-27.3: A MUTUAL LEARNING FRAMEWORK FOR FEW-SHOT SOUND EVENT DETECTION
Dongchao Yang, Helin Wang, Yuexian Zou, Zhongjie Ye, Peking University, China; Wenwu Wang, University of Surrey, United Kingdom of Great Britain and Northern Ireland
AUD-27.4: ANOMALOUS SOUND DETECTION USING SPECTRAL-TEMPORAL INFORMATION FUSION
Youde Liu, Jian Guan, Harbin Engineering University, China; Qiaoxi Zhu, University of Technology Sydney, Australia; Wenwu Wang, University of Surrey, United Kingdom of Great Britain and Northern Ireland
AUD-27.5: SPARSE SELF-ATTENTION FOR SEMI-SUPERVISED SOUND EVENT DETECTION
Yadong Guan, Jiabin Xue, Guibin Zheng, Jiqing Han, Harbin Institute of Technology, China
AUD-27.6: PEER COLLABORATIVE LEARNING FOR POLYPHONIC SOUND EVENT DETECTION
Hayato Endo, Hiromitsu Nishizaki, University of Yamanashi, Japan