The consortium members will promote Repertorium’s outcomes through workshops, conferences, publications, and educational initiatives, advancing the fields of musicology, musical practice, and sound processing while making an important contribution to the creation of musical AI systems that can evolve a sense of European identity, tastes, culture, and values by training on its heritage.

Open Source

Resulting optical music recognition tools for medieval and classical manuscripts, music information retrieval medieval cataloguing tools, and instrumental sound source separation and sound field reconstruction testing materials will be licenced under Creative Commons licences (Attribution, Non-Commercial, Share Alike, CC BY-NC-SA) and delivered to public repositories. All training data will be licenced as public domain and shared to allow for the reproducibility of the research. In those cases in which partners intend to seek patents for their machine learning algorithms, sufficient materials will be granted to ensure the reproducibility of scientific results while protecting the partner’s intellectual property.

Outputs

Software & Demos

Neumz JNABC

Repos

Spheres Sound Samples

Publications

Pezzoli, M., Antonacci, F., & Sarti, A. (2023). Implicit neural representation with physics-informed neural networks for the reconstruction of the early part of room impulse responses.

Diaz-Guerra, D., Politis, A,, Miguel, A., Beltran, Jose R. and Virtanen, T. (2023) Permutation Invariant Recurrent Neural Networks for Sound Source Tracking Applications.

Cabanas-Molero, P., Munoz-Montoro, A., Carabias-Orti, J. and Vera-Candeas, P. (2023). Pre-trained Spatial Priors on Multichannel NMF for Music Source Separation. Forum Acusticum 2023.

Martinez Sevilla, Juan C. & Ríos Vila, Antonio & Castellanos, Francisco & Calvo-Zaragoza, Jorge. (2023). A Holistic Approach for Aligned Music and Lyrics Transcription.

F. Miotello, L. Comanducci, M. Pezzoli, A. Bernardini, F. Antonacci and A. Sarti, “Reconstruction of Sound Field Through Diffusion Models,” ICASSP 2024 – 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Korea, Republic of, 2024, pp. 1476-1480.

F. Miotello, P. Ostan, M. Pezzoli, L. Comanducci, A. Bernardini, F. Antonacci & A. Sarti (2024). HOMULA-RIR: A Room Impulse Response Dataset for Teleconferencing and Spatial Audio Applications.

Public Deliverables

D6.1 Communication, dissemination, and exploitation plan I

D6.2 Communication, dissemination, and exploitation plan II

D7.2 Data Management Plan I

Talks and Presentations

20 July 2023

IIIF Neume Workshop

Juan Carlos Martínez Sevilla, Dominique Crochu, John Anderson: Presentation on Repertorium’s objectives and strategies with IIIF Neume Workshop, Centro de Estudios de Sociologia e Estética Musical, Colégio Almada Negreiros, Universidade Nova de Lisboa, hosted by Elsa De Luca for the project ECHOES.

San José, California, August 21-23 2023

ICDAR 2023

Juan Carlos Martínez Sevilla presented the work A Holistic Approach for Aligned Music and Lyrics Transcription.

11th – 15th September 2023
Turin, Italy - Politecnico di Torino

Forum Acusticum

Pezzoli M, Antonacci F, Sarti A: Implicit Neural Representation with Physics-Informed Neural Networks for the Reconstruction of the Early Part of Room Impulse Responses. 10th Convention of the European Acoustics Association.