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.

Noise2Music

Google Research · 2023

A diffusion-based model to generate music from text prompts and demonstrate its capability by generating 30-second long 24kHz music clips.

Application types: Text-to-music

Architecture:Diffusion

Essential categories

Category	Status	Notes
Source code	✘ Closed	No source codebase is available.
Training data	~ Partial	Training data is described in detail. However, the resulting MuLaMCap dataset resulting from this work is not publicly available.
Model weights	✘ Closed	Model weights are not available.
Code documentation	✘ Closed	No codebase is available. There is no documentation available either.
Training procedure	~ Partial	The available pre-print describes partially the training procedure of the model. While some relevant information is described, such as model configuration and training details, there are key aspects of the training missing, such as hardware requirements, model checkpoints and hyperparameters.
Evaluation procedure	~ Partial	Despite the evaluation procedure is well-documented in regards to evaluation data and metrics, the evaluation process lacks some relevant details to ensure replicability. Moreover, evaluation code of the system is not available.
Research paper	~ Partial	Preprint is available. No peer-reviewed version of the article has been found.
Licensing	✘ Closed	Not available.

Desirable categories

Category	Status	Notes
Model card	∅ Not included	Not available.
Datasheet	∅ Not included	Not available.
Package	∅ Not included	Not available.
User-oriented application	∅ Not included
Supplementary material page	⭐ Included	Complementary site with sound examples is available.

Raw YAML file with complete evaluation.