Current advancements on the naturalness and expressiveness of machine learning models for music generation have raised questions about the ethical, legal, cultural and social impact that those systems may have, including the works of musicians, producers and the listening experiences.

This project deals with the concept of trustworthiness in AI-powered music generation systems. The goal is to investigate how explainability and transparency can be used to inform listeners and other stakeholders about the degree to which AI technologies are involved in the music they listen to, and to relate generated music with the different components of the generation model, i.e. the dataset, algorithm (e.g. neural network architecture) and the different humans involved in the process (e.g. developer, dataset curator, composer of pieces used for training).

This project is a private-public collaboration involving Sony Group Corporation, the Joint Research Center of the European Commission, and the Music Technology Group (UPF). The project is coordinated by Yuki Mitsufuji and Weihsiang Liao (SONY), Emilia Gómez (JRC-MTG) and Xavier Serra (MTG). The research in this project will be part of the Industrial PhD of Roser Batlle.

Project information: TRAMUCA