Music Information Retrieval and Recommendation: Recent and Future Developments

Abstract

Music information retrieval allows to build new tools for music creation and appreciation based on information in music and how people perceive and interact with it. In this talk, I will present recent research directions in music information retrieval and recommendation at my lab, touching upon various topics such as semantic control of music generation systems, deep learning architectures for music tagging, and reproducibility of user studies in MIR. I will also highlight upcoming projects, such as transformer-based drum pattern generation, sequential music recommendation, and chill factor detection in music to identify common research interests with the faculty at the School of Music.