Can Machines Generate Personalized Music? A Hybrid Favorite-aware Method for User Preference Music Transfer
Zhejing Hu, Yan Liu, Gong Chen, and Yongxu Liu

TL;DR
This paper explores the novel problem of user preference music transfer (UPMT), aiming to generate personalized music by transferring user preferences, and introduces a hybrid favorite-aware method to address this challenge.
Contribution
It proposes a new hybrid favorite-aware approach for personalized music transfer, filling a gap in existing music style transfer research.
Findings
Demonstrates effectiveness of the proposed method in personalized music transfer
Achieves higher user satisfaction compared to baseline models
Provides a new framework for user preference modeling in music
Abstract
User preference music transfer (UPMT) is a new problem in music style transfer that can be applied to many scenarios but remains understudied.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMusic and Audio Processing · Music Technology and Sound Studies · Speech and Audio Processing
