AUD-4.2
MUSIC PHRASE INPAINTING USING LONG-TERM REPRESENTATION AND CONTRASTIVE LOSS
Shiqi Wei, Weiguo Gao, Fudan University, China; Gus Xia, Liwei Lin, New York University Shanghai, China; Yixiao Zhang, Queen Mary University of London, United Kingdom of Great Britain and Northern Ireland
Session:
Symbolic Analysis and Synthesis of Music
Track:
Audio and Acoustic Signal Processing
Location:
Gather Area K
Presentation Time:
Sun, 8 May, 22:00 - 22:45 China Time (UTC +8)
Sun, 8 May, 14:00 - 14:45 UTC
Sun, 8 May, 14:00 - 14:45 UTC
Session Chair:
Magdalena Fuentes, New York University
Session AUD-4
AUD-4.1: Audio-to-symbolic Arrangement via Cross-modal Music Representation Learning
Ziyu Wang, Gus Xia, NYU Shanghai, China; Dejing Xu, Tencent ARC Lab, China; Ying Shan, Tencnet ARC Lab, China
AUD-4.2: MUSIC PHRASE INPAINTING USING LONG-TERM REPRESENTATION AND CONTRASTIVE LOSS
Shiqi Wei, Weiguo Gao, Fudan University, China; Gus Xia, Liwei Lin, New York University Shanghai, China; Yixiao Zhang, Queen Mary University of London, United Kingdom of Great Britain and Northern Ireland
AUD-4.3: MELONS: GENERATING MELODY WITH LONG-TERM STRUCTURE USING TRANSFORMERS AND STRUCTURE GRAPH
Yi Zou, Communication University of China, China; Pei Zou, Peking University, China; Yi Zhao, Ran Zhang, Xiaorui Wang, Kuaishou Technology Co., Beijing, China; Kaixiang Zhang, Kuaishou Technology Co, China
AUD-4.4: DIFFICULTY-AWARE NEURAL BAND-TO-PIANO SCORE ARRANGEMENT BASED ON NOTE- AND STATISTIC-LEVEL CRITERIA
Moyu Terao, Yuki Hiramatsu, Ryoto Ishizuka, Yiming Wu, Kazuyoshi Yoshii, Kyoto University, Japan
AUD-4.5: SCORE DIFFICULTY ANALYSIS FOR PIANO PERFORMANCE EDUCATION BASED ON FINGERING
Pedro Ramoneda, Music Technology Group (MTG), Spain; Nazif Can Tamer, Vsevolod Eremenko, Xavier Serra, Marius Mirón, MTG, Spain
AUD-4.6: HARMONIC-TEMPORAL FACTOR DECOMPOSITION FOR UNSUPERVISED MONAURAL SEPARATION OF HARMONIC SOUNDS
Tomohiko Nakamura, University of Tokyo, Japan; Hirokazu Kameoka, Nippon Telegraph and Telephone Corporation, Japan