TOMI uses a four-node structure plus LLM in-context learning to turn sample clips into whole multi-track electronic songs with planned section structure.
The proposed data structure integrates symbolic and audio representations and can be manipulated by text-based LLMs via ICL
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TOMI: Transforming and Organizing Music Ideas for Multi-Track Compositions with Full-Song Structure
TOMI uses a four-node structure plus LLM in-context learning to turn sample clips into whole multi-track electronic songs with planned section structure.