AASP-L8.3
MERTECH: INSTRUMENT PLAYING TECHNIQUE DETECTION USING SELF-SUPERVISED PRETRAINED MODEL WITH MULTI-TASK FINETUNING
Dichucheng Li, Fudan University, China; Yinghao Ma, Queen Mary University of London, United Kingdom of Great Britain and Northern Ireland; Weixing Wei, Fudan University, China; Qiuqiang Kong, The Chinese University of Hong Kong, Hong Kong; Yulun Wu, Fudan University, China; Mingjin Che, Fan Xia, Sichuan Conservatory of Music, China; Emmanouil Benetos, Queen Mary University of London, United Kingdom of Great Britain and Northern Ireland; Wei Li, Fudan University, China
Session:
AASP-L8: Music Signal Analysis and Processing Lecture
Track:
Audio and Acoustic Signal Processing
Location:
Room 101
Presentation Time:
Thu, 18 Apr, 09:00 - 09:20 (UTC +9)
Session Co-Chairs:
Zafar Rafii, Audible Magic and Li Su, Academia Sinica
Session AASP-L8
AASP-L8.1: UNSUPERVISED PITCH-TIMBRE DISENTANGLEMENT OF MUSICAL INSTRUMENTS USING A JACOBIAN DISENTANGLED SEQUENTIAL AUTOENCODER
Yin-Jyun Luo, Queen Mary University of London, United Kingdom of Great Britain and Northern Ireland; Sebastian Ewert, Spotify, Sweden; Simon Dixon, Queen Mary University of London, United Kingdom of Great Britain and Northern Ireland
AASP-L8.2: IMPROVING MUSIC SOURCE SEPARATION WITH SIMO STEREO BAND-SPLIT RNN
Yi Luo, Rongzhi Gu, Tencent AI Lab, China
AASP-L8.3: MERTECH: INSTRUMENT PLAYING TECHNIQUE DETECTION USING SELF-SUPERVISED PRETRAINED MODEL WITH MULTI-TASK FINETUNING
Dichucheng Li, Fudan University, China; Yinghao Ma, Queen Mary University of London, United Kingdom of Great Britain and Northern Ireland; Weixing Wei, Fudan University, China; Qiuqiang Kong, The Chinese University of Hong Kong, Hong Kong; Yulun Wu, Fudan University, China; Mingjin Che, Fan Xia, Sichuan Conservatory of Music, China; Emmanouil Benetos, Queen Mary University of London, United Kingdom of Great Britain and Northern Ireland; Wei Li, Fudan University, China
AASP-L8.4: ENRICHING MUSIC DESCRIPTIONS WITH A FINETUNED-LLM AND METADATA FOR TEXT-TO-MUSIC RETRIEVAL
SeungHeon Doh, KAIST, Korea, Republic of; Minhee Lee, Dasaem Jeong, Sogang University, Korea, Republic of; Juhan Nam, KAIST, Korea, Republic of
AASP-L8.5: ON THE CHOICE OF THE OPTIMAL TEMPORAL SUPPORT FOR AUDIO CLASSIFICATION WITH PRE-TRAINED EMBEDDINGS
Aurian Quelennec, Michel Olvera, Geoffroy Peeters, Slim Essid, Institut Polytechnique de Paris, France
AASP-L8.6: SYNTHTAB: LEVERAGING SYNTHESIZED DATA FOR GUITAR TABLATURE TRANSCRIPTION
Yongyi Zang, Yi Zhong, Frank Cwitkowitz, Zhiyao Duan, University of Rochester, United States of America
Contacts