AUD-12.4
DEEPCHORUS: A HYBRID MODEL OF MULTI-SCALE CONVOLUTION AND SELF-ATTENTION FOR CHORUS DETECTION
Qiqi He, Xiaoheng Sun, Wei Li, Fudan University, School of Computer Science and Technology, China, China; Yi Yu, National Institute of Informatics (NII), Tokyo, Japan, Japan
Session:
Musical Event Detection and Structure Analysis
Track:
Audio and Acoustic Signal Processing
Location:
Gather Area K
Presentation Time:
Mon, 9 May, 23:00 - 23:45 China Time (UTC +8)
Mon, 9 May, 15:00 - 15:45 UTC
Mon, 9 May, 15:00 - 15:45 UTC
Session Chair:
Nicholas Bryan, CCRMA Stanford University
Session AUD-12
AUD-12.1: MUSICYOLO: A SIGHT-SINGING ONSET/OFFSET DETECTION FRAMEWORK BASED ON OBJECT DETECTION INSTEAD OF SPECTRUM FRAMES
Xianke Wang, Wei Xu, Weiming Yang, Wenqing Cheng, Huazhong University of Science and Technology, China
AUD-12.2: MODELING BEATS AND DOWNBEATS WITH A TIME-FREQUENCY TRANSFORMER
Yun-Ning Hung, Georgia Institute of Technology, United States of America; Ju-Chiang Wang, Xuchen Song, Wei-Tsung Lu, Minz Won, ByteDance, United States of America
AUD-12.3: HIERARCHICAL CLASSIFICATION OF SINGING ACTIVITY, GENDER, AND TYPE IN COMPLEX MUSIC RECORDINGS
Michael Krause, Meinard Müller, International Audio Laboratories Erlangen, Germany
AUD-12.4: DEEPCHORUS: A HYBRID MODEL OF MULTI-SCALE CONVOLUTION AND SELF-ATTENTION FOR CHORUS DETECTION
Qiqi He, Xiaoheng Sun, Wei Li, Fudan University, School of Computer Science and Technology, China, China; Yi Yu, National Institute of Informatics (NII), Tokyo, Japan, Japan
AUD-12.5: TO CATCH A CHORUS, VERSE, INTRO, OR ANYTHING ELSE: ANALYZING A SONG WITH STRUCTURAL FUNCTIONS
Ju-Chiang Wang, Jordan B. L. Smith, ByteDance, United States of America; Yun-Ning Hung, Georgia Institute of Technology, United States of America
AUD-12.6: A NOVEL 1D STATE SPACE FOR EFFICIENT MUSIC RHYTHMIC ANALYSIS
Mojtaba Heydari, Zhiyao Duan, University of Rochester, United States of America; Matthew McCallum, Andreas Ehmann, Pandora Media, Inc., United States of America