News Release

Artificial intelligence to determine which music broadcast on TV is subject to copyright

The spin-off of the UPF BMAT and the Music Technology Group (MTG) receive an INNOTEC grant to develop LoudSense, an algorithm that will establish what music broadcast on television productions fulfils audibility requirements for copyright

Grant and Award Announcement

Universitat Pompeu Fabra - Barcelona

The music of television productions is a major source of revenue for the music industry thanks to copyright. Copyright can only be exercised when the music is sufficiently audible, but this is difficult to determine depending on the context. For example, our perception can vary when other sounds, such as conversation, are superimposed.

In order to provide a tool to solve this problem, the spinoff of the UPF BMAT and the Music Technology Group (MTG) are collaborating to develop new technology that automatically and objectively establishes the degree of audibility of background music and thus determine when copyright should be enforced.

"We aim to provide the international music industry with an innovative service that helps distribute copyright among its rightful owners more fairly, efficiently and transparently"

The project, called LoudSense, has received an Innotec grant in the 2020 announcement. This programme, which promotes technology transfer, provides funding to R&D projects executed jointly by enterprise and research groups accredited with the TECNIO seal.

The grant, awarded by ACCIÓ, the Catalan Government agency for business competitiveness, has awarded to BMAT and the MTG 146,197 euros to develop their technology over two years.

"We aim to provide the international music industry with an innovative service that helps distribute copyright among its rightful owners more fairly, efficiently and transparently", sums up Gonçal Calvo, in charge of innovation at BMAT.

The development of the technology

This project will consist of two phases. In the first, the MTG will carry out a series of experiments related to human perception of sound to establish what features music must have in order to be considered audible depending on the context. The results of this study will help researchers to establish criteria and generate a data set.

In the second phase, BMAT will take advantage of all the information generated in the experiments to develop an algorithm based on artificial intelligence that will automatically determine when music is audible, which will enable objectively establishing whether to generate copyright.

LoudSense will have "a highly significant impact on the market because will solve a music industry problem that causes a great deal of controversy and for which currently no-one is able to offer a service like this"

LoudSense will have "a highly significant impact on the market because will solve a music industry problem that causes a great deal of controversy and for which currently no-one is able to offer a service like this", Calvo assures.

An industrial doctorate success story

The seed for LoudSense arose thanks to the Catalan Government's Industrial doctorates programme, which promotes conducting doctoral theses within the framework of collaborative applied research projects between enterprise and universities. In the 2016 edition, BMAT and the MTG cooperated in this programme with a thesis on technology capable of detecting and automatically categorizing background and foreground music.

"The industrial doctorate was a success story because university-industry collaboration worked very well and laid the foundations for launching LoudSense. In addition, the investigator who was then a PhD fellow is now a PhD and continues to work on the project", explains Sonia Espí, promoter of the MTG.

Benefits of collaboration

This knowledge transfer project has several benefits from the point of view of the MTG: "first, thanks to the identification of problems and market needs, we manage to maximize the impact of our research in the real world, in this case the music industry; second, working together with enterprise will help us improve our technologies and capabilities", Espí judges.

The head of innovation at BMAT adds that collaboration with the research group will allow the company to "tackle a challenge that goes beyond the current state of the art" and enhance its music monitoring services and technologies "to gain a competitive advantage and market share".

With the support of ACCIÓ

###


Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.