The AudioCommons kick-off meeting will take place on Tuesday 19th and Wednesday 20th of January 2016 at Universitat Pompeu Fabra, Barcelona, Spain. We are therefore now officially ready to start with this new and exciting project and initiative. Besides the internal meetings of the consortium, the kick-off event will include an open presentations session in which we will go over the core ideas behind this initiative and each of the partners will introduce what is being done, and what will be done, in relation to AudioCommons. The open presentations session will take place on Wednesday 20th starting at 10h in room 55.309 of Poblenou Campus (UPF), and will include the following talks:

  • 10h MTG, Universitat Pompeu Fabra - Xavier Serra and Frederic Font. Presentation of the key concepts and goals of the AudioCommons project and of the envisioned Audio Commons Ecosystem. Overview the AudioCommons-related research being done at the MTG and the different projects and technologies that will be connected into the Audio Commons Ecosystem: Freesound, AcousticBrainz and Essentia.

  • 10:30h CoDE / IoSR / CVSSP, University of Surrey - Mark D. Plumbley, Tim Brookes and David Plans. Presentations of the three centers involved, Centre for the Digital Economy (CoDE), Institute of Sound Recording (IoSR), and Centre for Vision Speech and Signal Processing (CVSSP), and of the research to be done in AudioCommons. CoDE will investigate and develop frameworks to understand and analyse emerging digital business models in audio and the creative industries, IoSR will develop models of timbral perception to allow automated semantic annotation of non-musical content. CVSSP will develop novel signal processing algorithms to facilitate automated semantic annotation of non-musical content.

  • 11h C4DM, Queen Mary University of London - George Fazekas and Mathieu Barthet. Review of the research and tools developed at the C4DM related to the AudioCommons initiative, such as the Music Ontology, the Vamp audio analysis framework, Sonic Visualiser, Sonic Annotator, or the Web-based environment SAWA. Presentation of the recent work in affective computing, which aims at annotating music by mood using audio and social information.

  • 12h Jamendo - Martin Guerber and Samuel Devyver. Brief overview of Jamendo (history, philosophy, current directions) and presentation of Jamendo Music (platform for music lovers to discover and enjoy music freely, and for artists to promote themselves and make money) and Jamendo Licensing (marketplace to sell royalty-free music licenses for commercial use). Discussion of the current approach for dealing with music metadata and audio content qualification as it relates to the AudioCommons project.

  • 12:30h AudioGaming - Amaury La Burthe. Presentation of AudioGaming and its philosophy (initial starting idea, recent evolutions) and a presentation of the tools that have been already developed and that are planned for development within the AudioCommons project and that could be seamlessly linked to Creative Commons audio databases. Discussion on the integration and Creative Commons usage challenges from an interactive/video game perspective.

  • 13h Waves - Yuvai Levi. Presentation of Waves and of a working prototype of a standalone application which can browse and query online audio repositories acting as a web server, and an audio plugin which communicates with the former web server to enable queries from the plugin itself. Discussion over the possibilities of presenting/serving the rights issues of the sample owners, and some other ideas regarding the usage of automatic audio analysis algorithms for the sake of improving search results of audio in online repositories which do not support advanced search functionalities.