MusGO Framework: Assessing Openness in Music-Generative AI

This website builds on the paper MusGO: A Community-Driven Framework for Assessing Openness in Music-Generative AI, authored by Roser Batlle-Roca, Laura Ibáñez-Martínez, Xavier Serra, Emilia Gómez, and Martín Rocamora, and published in the Proceedings of the 26th International Society for Music Information Retrieval Conference (ISMIR 2025). It serves not only as a companion to the publication, but also as a living resource, which is continuously updated and shaped by contributions from the community.

Music ControlNet

Carnegie Mellon University and Adobe Research · 2023

Generative model that offers multiple precise, time-varying controls over generated audio.

Application types: Melody-to-musicText-to-music

Architecture:Diffusion

Essential categories

Category	Status	Notes
Source code	✘ Closed	No official code repository available.
Training data	✘ Closed	Very limited description of the data used for training, and no sources provided.
Model weights	✘ Closed	No model weights provided.
Code documentation	✘ Closed	No source code available so no documentation.
Training procedure	✔︎ Open	Training procedure is described in detail in the paper.
Evaluation procedure	~ Partial	Evaluation procedure is described, but details on the specific implementation used for some of the evaluation metrics are not given, limiting the reproducibility of results.
Research paper	✔︎ Open	Accepted at IEEE/ACM Transactions on Audio, Speech, and Languange Processing (open access).
Licensing	✘ Closed	Not available.

Desirable categories

Category	Status	Notes
Model card	∅ Not included	No model card available.
Datasheet	∅ Not included	No datasheet available.
Package	∅ Not included	No package available.
User-oriented application	∅ Not included	No user interface nor real-time implementation available.
Supplementary material page	⭐ Included	A complementary website with sound examples and demo of the model is available.

Raw YAML file with complete evaluation.