How Close to the Theme? Similarity-Label Conditioning for Game Music Generation
cs.SD, cs.LG, eess.AS
Submitted: 2026-10-31
Updated: 2026-11-03
Comments: 39 pages, 6 figures, 10 tables, including supplementary material. Submitted to Computer Music Journal. Code: https://github.com/ShxLuo-Saxon/simllama ; data: https://github.com/ShxLuo-Saxon/supermario-structure-dataset ; audio examples: https://shxluo-saxon.github.io/simllama/
Code: https://github.com/ShxLuo-Saxon/simllama
Project page: https://shxluo-saxon.github.io/simllama/Acknowledgments
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- ImprovNet -- Generating Controllable Musical Improvisations with Iterative Corruption Refinement
- Gemini: A Family of Highly Capable Multimodal Models
- Moonbeam: A MIDI Foundation Model Using Both Absolute and Relative Music Attributes
- FIGARO: Generating Symbolic Music with Fine-Grained Artistic Control
- LLaMA: Open and Efficient Foundation Language Models
- Whole-Song Hierarchical Generation of Symbolic Music Using Cascaded Diffusion Models
Related papers
- Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
- MuLaCover: Flexible Cover Song Generation via Symbolic Tonal Control
- Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems