My research is motivated by my background in both engineering and music, and is centred around the Music Information Retrieval (MIR) field. I try to understand the way humans describe music (in terms of melody, tonality, similarity, style or emotion) and use this knowledge to build applications to enhance music listening experiences. My research is interdisciplinary and incorporates knowledge from signal processing, music theory, cognition and artificial intelligence.
Starting from the music domain, I also research on the impact of artificial intelligence (AI) into human behaviour. In particular, I am interested on the interaction between humans and algorithms, how AI impacts cognitive and socio-emotional development and the impact of algorithms in human decision making.
Current research projects:
- Human behaviour and Machine Intelligence– HUMAINT (Lead Scientist) Centre for Advanced Studies, Joint Research Centre, European Commission, 2018-2020.
- Towards Richer Online Music Public-domain Archives- TROMPA (PI), H2020 project coordinated by Universitat Pompeu Fabra, Barcelona, May 2018- February 2020.
- Cante Flamenco Tech (Technical development) – Technologies for learning to sing flamenco, personal project.
- Banda sonora vital (Researcher) – Technologies for life sound recovery and music recommendation for people with dementia, personal project.
- CASAS (PI – Spanish Government): Community Assisted Singing Analysis and Synthesis 2016-2018.
- Gathering and Modelling Large-scale Crowdsourced Multimedia Music Data.
2016-2017, co-PI with Gloria Haro of an internal project part of the María de Maeztu program funded by the Spanish Government.
- PHENICX (PI – European Commission FP7 STREP): Changing the way we experience classical music concerts.
Main technologies (software) I have contributed to:
- Essentia: Open-source library and tools for audio and music analysis, description and synthesis (with MTG group).
MELODIA: Melody extraction vamp plugin (with Justin Salamon)
- HPCP: Harmonic Pitch Class Profiles vamp plugin (with Jordi Bonada)
- Matlab toolbox for multi-scale set-class analysis (with Agustín Martorell)
- CANTE: Automatic transcription of flamenco singing, open source (with Nadine Kroher)
I was also a co-founder of BMAT.