Repertorium will revolutionise music scholarship, enhance streaming revenues, and empower musicians.
A suite of AI tools to protect and explore Europe’s ancient musical roots and which develop out of this heritage innovative technological solutions to empower the future of the music industry.
REPERTORIUM uses AI to digitise ancient and classical manuscripts, preserve European musical heritage, and create state-of-the-art sound processing technologies, including metaverse-ready immersive audio.
These technologies are the foundation of a general musical artificial intelligence that fully unleashes the powers of machine learning upon the domain of European classical heritage, advancing us towards a human-centred digital world.
REPERTORIUM is funded by the European Union through a Horizon Research and Innovation grant.
Digitising ancient manuscripts from the Solesmes archive for musicological study, thousands of hours of audio recordings, and creating linked databases for medieval and classical works.
Combining multimodal artificial intelligence and deep learning solutions to perform optical music recognition and music information retrieval across multiple music datasets.
AI-powered classical instrument sound source separation solutions with real-time sound field reconstruction. Split a symphony recording into its parts. Solo, remix or even mute a part.
Testing immersive technologies through streamed symphonic concerts. Choose your seat, move around, or experience it from the point of view of a musician on stage!
Revolutionising music scholarship, enhancing streaming revenues, and empowering music students to create minus-one versions of their favourite recordings.
The Future from our Past
Repertorium is a Horizon Europe Research and Innovation Project funded by the European Union, with a focus on promoting European cultural heritage.
Presentation on Neural Networks for Sound Source Tracking Applications
David Guerra presented his paper Permutation Invariant Recurrent Neural Networks for Sound Source Tracking Applications at the 10th Convention of the European Acoustics...
Presentation on Pre-trained Spatial Priors for Music Source Separation
Antonio Muñoz, Pedro Vera and Julio Carabias presented their paper Pre-trained Spatial Priors on Multichannel NMF for Music Source Separation at the 10th Convention...
Presentation on Physics-Informed Neural Networks for Sound Processing
Mirco Pezzoli and Fabio Antonacci presented their paper Implicit Neural Representation with Physics-Informed Neural Networks for the Reconstruction of the Early Part of...
Juan Carlos Martínez Sevilla presented his paper “A Holistic Approach for Aligned Music and Lyrics Transcription” at the International Conference on Document Analysis...
Recording of Tridentine Rite begins at Abbaye St Magdalene
John Anderson, Fabio Cardone, and Thomas Vingtrinier installed a state-of-the-art recording system in the abbey’s chapel, which will automatically record all offices and...