TOMI: Transforming and Organizing Music Ideas for Multi-Track Compositions with Full-Song Structure

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: He, Qi, Xia, Gus, Wang, Ziyu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915364047159296
author He, Qi
Xia, Gus
Wang, Ziyu
author_facet He, Qi
Xia, Gus
Wang, Ziyu
contents Hierarchical planning is a powerful approach to model long sequences structurally. Aside from considering hierarchies in the temporal structure of music, this paper explores an even more important aspect: concept hierarchy, 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 segments), 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 workstation, enabling interactive human-AI co-creation. Experimental results demonstrate that our approach produces higher-quality electronic music with stronger structural coherence compared to baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2506_23094
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TOMI: Transforming and Organizing Music Ideas for Multi-Track Compositions with Full-Song Structure
He, Qi
Xia, Gus
Wang, Ziyu
Sound
Artificial Intelligence
Audio and Speech Processing
Hierarchical planning is a powerful approach to model long sequences structurally. Aside from considering hierarchies in the temporal structure of music, this paper explores an even more important aspect: concept hierarchy, 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 segments), 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 workstation, enabling interactive human-AI co-creation. Experimental results demonstrate that our approach produces higher-quality electronic music with stronger structural coherence compared to baselines.
title TOMI: Transforming and Organizing Music Ideas for Multi-Track Compositions with Full-Song Structure
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2506.23094