AUD-9.3
IMPROVED REPRESENTATION LEARNING FOR ACOUSTIC EVENT CLASSIFICATION USING TREE-STRUCTURED ONTOLOGY
Arman Zharmagambetov, University of California, Merced, United States of America; Qingming Tang, Chieh-Chi Kao, Qin Zhang, Ming Sun, Viktor Rozgic, Jasha Droppo, Chao Wang, Amazon, Alexa, United States of America
Session:
Detection and Classification of Acoustic Scenes and Events III: Losses and Training
Track:
Audio and Acoustic Signal Processing
Location:
Gather Area K
Presentation Time:
Mon, 9 May, 21:00 - 21:45 China Time (UTC +8)
Mon, 9 May, 13:00 - 13:45 UTC
Mon, 9 May, 13:00 - 13:45 UTC
Session Chair:
Romain Serizel, LORIA
Session AUD-9
AUD-9.1: TIME-BALANCED FOCAL LOSS FOR AUDIO EVENT DETECTION
Sangwook Park, Mounya Elhilali, Johns Hopkins University, United States of America
AUD-9.2: MULTI-ACCDOA: LOCALIZING AND DETECTING OVERLAPPING SOUNDS FROM THE SAME CLASS WITH AUXILIARY DUPLICATING PERMUTATION INVARIANT TRAINING
Kazuki Shimada, Yuichiro Koyama, Shusuke Takahashi, Naoya Takahashi, Emiru Tsunoo, Yuki Mitsufuji, Sony Group Corporation, Japan
AUD-9.3: IMPROVED REPRESENTATION LEARNING FOR ACOUSTIC EVENT CLASSIFICATION USING TREE-STRUCTURED ONTOLOGY
Arman Zharmagambetov, University of California, Merced, United States of America; Qingming Tang, Chieh-Chi Kao, Qin Zhang, Ming Sun, Viktor Rozgic, Jasha Droppo, Chao Wang, Amazon, Alexa, United States of America
AUD-9.4: TEMPORAL CONTRASTIVE-LOSS FOR AUDIO EVENT DETECTION
Sandeep Kothinti, Mounya Elhilali, Johns Hopkins University, United States of America
AUD-9.5: A FRAME LOSS OF MULTIPLE INSTANCE LEARNING FOR WEAKLY SUPERVISED SOUND EVENT DETECTION
Xu Wang, Xiangjinzi Zhang, Shengwu Xiong, School of Computer and Artificial Intelligence, Wuhan University of Technology, Wuhan, China, China; Yunfei Zi, ,
AUD-9.6: PSEUDO STRONG LABELS FOR LARGE SCALE WEAKLY SUPERVISED AUDIO TAGGING
Heinrich Dinkel, Zhiyong Yan, Yongqing Wang, Junbo Zhang, Yujun Wang, Xiaomi Corporation, China