Perez, MiguelKirchhoff, HolgerGrosche, PeterSerra, Xavier2025-10-162025-10-162025Perez M, Kirchhoff H, Grosche P, Serra X. Singing voice accompaniment data augmentation with generative models. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2025 April 6-11; Hyderabad, Índia. 5 p. DOI: 10.1109/ICASSPW65056.2025.11011167http://hdl.handle.net/10230/71522Singing voice transcription is a key task in Music Information Retrieval (MIR) that focuses on identifying sung notes within a music audio segment. Advancing state-of-theart methods in this area relies heavily on high-quality data, yet annotating such data is resource-intensive and requires musical expertise. In genres like pop music, data sharing is further complicated by copyright and distribution limitations. In this paper, we refine a recently proposed data augmentation technique that leverages AI-generated music audio to address these data-related challenges. Specifically, we create musical accompaniments for vocals with known target notes, enabling the generation of new mixes that retain the original piece’s harmony while introducing substantial audio variation. Our cross-dataset experiments reveal that using harmony-matched mixes improves generalization, though performance remains below that achieved by training with additional real data.application/pdfeng© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. http://dx.doi.org/10.1109/ICASSPW65056.2025.11011167info:eu-repo/semantics/conferenceObjectSinging voiceData augmentationGenerative modelsinfo:eu-repo/semantics/openAccess