AUD-20.2
S3T: SELF-SUPERVISED PRE-TRAINING WITH SWIN TRANSFORMER FOR MUSIC CLASSIFICATION
Hang Zhao, Bilei Zhu, Zejun Ma, ByteDance, China; Chen Zhang, Kejun Zhang, Zhejiang University, China
Session:
Music Classification, Identification, and Melody Extraction
Track:
Audio and Acoustic Signal Processing
Location:
Gather Area L
Presentation Time:
Wed, 11 May, 20:00 - 20:45 China Time (UTC +8)
Wed, 11 May, 12:00 - 12:45 UTC
Wed, 11 May, 12:00 - 12:45 UTC
Session Chair:
Yanfeng Lu, Institute for Infocomm Research, A*STAR
Session AUD-20
AUD-20.1: VIOLINIST IDENTIFICATION USING NOTE-LEVEL TIMBRE FEATURE DISTRIBUTIONS
Yudong Zhao, György Fazekas, Mark Sandler, Queen Mary University of London, United Kingdom of Great Britain and Northern Ireland
AUD-20.2: S3T: SELF-SUPERVISED PRE-TRAINING WITH SWIN TRANSFORMER FOR MUSIC CLASSIFICATION
Hang Zhao, Bilei Zhu, Zejun Ma, ByteDance, China; Chen Zhang, Kejun Zhang, Zhejiang University, China
AUD-20.3: AMBIGUITY MODELLING WITH LABEL DISTRIBUTION LEARNING FOR MUSIC CLASSIFICATION
Morgan Buisson, Pablo Alonso Jimenez, Dmitry Bogdanov, Universitat Pompeu Fabra, Spain
AUD-20.4: BYTECOVER2: TOWARDS DIMENSIONALITY REDUCTION OF LATENT EMBEDDING FOR EFFICIENT COVER SONG IDENTIFICATION
Xingjian Du, Zijie Wang, Bilei Zhu, Zejun Ma, Bytedance AI Lab, China; Ke Chen, University of California San Diego, China
AUD-20.5: TONET: TONE-OCTAVE NETWORK FOR SINGING MELODY EXTRACTION FROM POLYPHONIC MUSIC
Ke Chen, Taylor Berg-Kirkpatrick, Shlomo Dubnov, University of California San Diego, United States of America; Shuai Yu, Wei Li, Fudan University, China; Cheng-i Wang, Smule Inc., United States of America
AUD-20.6: Hierarchical Graph-based Neural Network for Singing Melody Extraction
Shuai Yu, Xi Chen, Wei Li, Fudan University, China