TOMI: TRANSFORMING AND ORGANIZING MUSIC IDEAS FOR MULTI-TRACK COMPOSITIONS WITH FULL-SONG STRUCTURE
He, Qi Xia, Gus Wang, Ziyu
He, Qi
Xia, Gus
Wang, Ziyu
Author
Supervisor
Department
Machine Learning
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Hierarchical planning is a powerful approach to model long sequences structurally. Aside from considering hi-erarchies in the temporal structure of music, this paper explores an even more important aspect: concept hierar-chy, which involves generating music ideas, transforming them, and ultimately organizing them—across musical time and space—into a complete composition. To this end, we introduce TOMI (Transforming and Organizing Music Ideas) as a novel approach in deep music generation and develop a TOMI-based model via instruction-tuned foundation LLM. Formally, we represent a multi-track composition process via a sparse, four-dimensional space characterized by clips (short audio or MIDI seg-ments), sections (temporal positions), tracks (instrument layers), and transformations (elaboration methods). Our model is capable of generating multi-track electronic music with full-song structure, and we further integrate the TOMI-based model with the REAPER digital audio work-station, enabling interactive human-AI co-creation. Experimental results demonstrate that our approach produces higher-quality electronic music with stronger structural co-herence compared to baselines.1.
Citation
Q. He, G. Xia, and Z. Wang, “TOMI: Transforming and Organizing Music Ideas for Multi-Track Compositions With Full-Song Structure,” Proceedings of the International Society for Music Information Retrieval Conference, vol. 2025, pp. 337–345, Sep. 2025, doi: 10.5281/ZENODO.17706410
Source
Proceedings of the International Society for Music Information Retrieval Conference
Conference
26th International Society for Music Information Retrieval Conference (ISMIR 2025)
Keywords
Subjects
Source
26th International Society for Music Information Retrieval Conference (ISMIR 2025)
Publisher
International Society for Music Information Retrieval