Researchers on the University of Alicante are growing a software based mostly on Artificial Intelligence (AI) for transcription of medieval scores. The group will deliver again to life greater than 4,000 items of Gregorian chant, which haven’t been seen for 1,000 years. For this undertaking, they may work with 400,000 photos of historic manuscriptsOptical Music Recognition can be used to extract data from manuscripts, such because the melody, the kind of liturgical ceremony or the liturgical cycle
Researchers from the University of Alicante are growing a software based mostly on Artificial Intelligence (AI) for transcription of medieval scores.
They are doing so inside the European undertaking Repertorium (Researching and Encouraging the Promulgation of European Repertory by Technologies Operating on Records Interrelated Utilizing Machines), which goals to protect Europe’s musical heritage and create state-of-the-art sound processing applied sciences, together with immersive audio prepared for the metaverse.
The professor of the Department of Languages and Computer Systems Jorge Calvo leads the UA group liable for the creation of an OMR (Optical Music Recognition, in its acronym in English) that can deliver again to life greater than 4,000 items of Gregorian chant, which haven’t seen the sunshine of day for greater than 1,000 years. In whole, they may work with 400,000 photos of historic manuscripts.
An important scientific problem
The OMR permits extracting data from digitized manuscripts, such because the melody, lyrics, kind of liturgical ceremony or place within the liturgical cycle. In the context of the Repertorium it’s a nice scientific problem as a result of the AI not solely has to grasp the symbols of musical notation but additionally acknowledge the textual content of the works and routinely interpret the way it must be sung.
Once the pc is able to processing sheet music photos and understanding them, the content material of the works might be transcribed effectively and precisely right into a digital rating format, permitting the applying of all types of digital applied sciences to hold out the goals of the undertaking, the educational establishment explains in a press release.
The undertaking started its journey final January and can run for 3 years. Repertorium is made up of a consortium whose members come from eight nations and is coordinated by the Escuela Politécnica Superior de Linares of the University of Jaén.
Partners additionally embody the University of Oxford, the Complutense Institute of Musical Sciences, the Hispanic Association for the Study of Gregorian Chant, the Polytechnic University of Milan, the University of Tampere, the artistic advertising and marketing firm VIST.CO from Hamburg, the UK developer Spork Digital, the French Association Musicologie Médiévale, the Lithuanian National Philharmonic Orchestra and the cultural know-how developer Odratek.
The undertaking will lay the technological foundations for the cataloging of music information
The Department of Language and Computer Systems of the University of Alicante has the most effective consultants in Optical Music Recognition on the earth. “We are the world leaders in OMR,” says Professor Calvo, who says that one of many challenges of this undertaking is that OCR (Optical Character Recognition) can be utilized on the identical time in order that the textual content and notes can be transcribed with a purpose to set up the connection between the 2.
The cataloged songs can be revealed in digital libraries to disseminate this content material, till now accessible solely to a small variety of consultants.
These 400,000 photos come from the archive of the Musical Paleography Workshop of the Abbey of Solesmes (France). Once digitized, they are going to be saved in DIAMM, the open platform of the University of Oxford, specialised in cataloging photos of historic musical manuscripts.
On the opposite hand, the data associated to the cataloging (metadata) can be listed within the portal of the Medieval Music Manuscripts Online Association (MMMO), accessible brazenly. Both methods can be interconnected with one another to keep away from duplication, guarantee consistency and facilitate the work of session.
The undertaking will lay the technological foundations for the method of cataloging music archives utilizing, amongst different issues, Artificial Intelligence methods, which can be made accessible, in open supply, in order that they are often utilized to different historic music archives.
Immersive live performance expertise
In addition, one other side will deal with growing applied sciences that permit a very immersive expertise in classical music live shows, in order that the person can work together with the orchestra for leisure or academic functions. This know-how will even be accessible to orchestras, in order that the general public can work together in immersive live shows by know-how and digital actuality platforms, thus selling the event of latest streaming markets and attracting new audiences.
Repertorium will publicize the applied sciences developed in cycles of conferences and gala’s, along with making ready academic materials and a sequence of publications for dissemination. Likewise, in its closing stage, the undertaking will supply a number of live shows and an opera in order that the person can expertise all this know-how in follow. Workshops will even be given in conservatories and music faculties.
Topics