AASP-P10: Music Generation I
Poster
Wed, 6 May, 14:00 - 16:00
Location: Poster Area 25
Session Type: Poster
Track: Audio and Acoustic Signal Processing [AA]
Click the to view the manuscript on IEEE Xplore Open Preview

AASP-P10.1: STEMPHONIC: ALL-AT-ONCE FLEXIBLE MULTI-STEM MUSIC GENERATION
Shih-Lun Wu, MIT, United States of America; Ge Zhu, Juan-Pablo Caceres, Adobe, United States of America; Cheng-Zhi Anna Huang, MIT, United States of America; Nicholas J. Bryan, Adobe, United States of America

AASP-P10.2: LOW-RESOURCE GUIDANCE FOR CONTROLLABLE LATENT AUDIO DIFFUSION
Zachary Novack, UC San Diego, United States of America; Zack Zukowski, CJ Carr, Julian Parker, Zach Evans, Josiah Taylor, Stability AI, United States of America; Taylor Berg-Kirkpatrick, Julian McAuley, UC San Diego, United States of America; Jordi Pons, Stability AI, United States of America

AASP-P10.3: DIFFUSION TIMBRE TRANSFER VIA MUTUAL INFORMATION GUIDED INPAINTING
Ching Ho Lee, Queen Mary, University of London, United Kingdom of Great Britain and Northern Ireland; Javier Nistal, Stefan Lattner, Sony CSL, France; Marco Pasini, George Fazekas, Queen Mary, University of London, United Kingdom of Great Britain and Northern Ireland

AASP-P10.4: D3PIA: A Discrete Denoising Diffusion Model for Piano Accompaniment Generation from Lead sheet
Eunjin Choi, Hounsu Kim, Hayeon Bang, Taegyun Kwon, Juhan Nam, Korea Advanced Institute of Science and Technology, Korea, Republic of

AASP-P10.5: MELOS: SENTENCE-TO-SECTION TRAINING WITH MULTI-TASK LEARNING FOR LLM-DRIVEN SONG GENERATION
Dapeng Wu, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China, China; Jinhong Lu, Bin Su, Wonderai, China; Shun Lei, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China, China; Xiong Cai, Wonderai, China; Zhiyong Wu, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China, China

AASP-P10.6: EVALUATING DISENTANGLED REPRESENTATIONS FOR CONTROLLABLE MUSIC GENERATION
Laura Ibáñez-Martínez, Chukwuemeka Nkama, Andrea Poltronieri, Xavier Serra, Martín Rocamora, Universitat Pompeu Fabra, Spain

AASP-P10.7: SYNTHCLONER: SYNTHESIZER-STYLE AUDIO TRANSFER VIA FACTORIZED CODEC WITH ADSR ENVELOPE CONTROL
Jeng-Yue Liu, Ting-Chao Hsu, Yen-Tung Yeh, National Taiwan University, Taiwan; Li Su, Academia Sinica, Taiwan; Yi-Hsuan Yang, National Taiwan University, Taiwan

AASP-P10.8: Instrument Generation Through Distributional Flow Matching and Test-Time Search
Qihui Yang, University of California San Diego, United States of America; Randal Leistikow, Yongyi Zang, Smule Labs, United States of America

AASP-P10.9: A GENERATIVE-FIRST NEURAL AUDIO AUTOENCODER
Jonah Casebeer, Ge Zhu, Zhepei Wang, Nicholas Bryan, Adobe Research, United States of America

AASP-P10.10: ALIGNING LANGUAGE MODELS FOR LYRIC-TO-MELODY GENERATION WITH RULE-BASED MUSICAL CONSTRAINTS
Hao Meng, Siyuan Zheng, Shuran Zhou, Qiangqiang Wang, Yang Song, Zuoyebang Education Technology, China