Community Research and Development Information Service - CORDIS

H2020

AudioCommons Report Summary

Project ID: 688382
Funded under: H2020-EU.2.1.1.

Periodic Reporting for period 1 - AudioCommons (Audio Commons: An Ecosystem for Creative Reuse of Audio Content)

Reporting period: 2016-02-01 to 2017-07-31

Summary of the context and overall objectives of the project

The digital value chain that connects content creators and content users follows a traditional model that has not yet been adapted to the modern communication society. The democratisation of multimedia content creation and the social web revolution have changed the way in which multimedia content is created, shared and (re)used all over the world. Online multimedia sharing has experienced a huge growth in the last decade, yielding significant amounts of user-generated multimedia resources, a big part of them shared under open licenses. Furthermore, significant amounts of professionally created multimedia content released with closed licenses, are now becoming available as their licenses expire, but nevertheless remain unused. At the same time, media industries (content users) need to reduce production costs in order to remain competitive. There is, therefore, an opportunity for media industries to incorporate such content in their productions, but there is a lack of technologies for easily accessing and incorporating that type of content in their creative workflows. Particularly in the case of sound and music, a huge amount of audio material is available and released under Creative Commons (CC) licenses, but there no practical ways to easily embed this content into production workflows. The aim of the AudioCommons project is to bring CC licensed audio content to the creative industries, enabling its creation, access, retrieval and reuse in innovative ways. The key objectives are:

- Enable the retrieval of audio content in innovative ways by bringing current state-of-the-art methods of semantic sound and music description to higher standards, and make these methods available as software packages.
- Develop and deploy the technological layer to allow the interconnection of all stakeholders that participate in an ecosystem of content, users, services and tools that create and reuse CC audio content (i.e. the Audio Commons Ecosystem).
- Create and set up the Audio Commons Ecosystem, publish CC audio content through it and build tools that can consume the content and be embedded in existing creative workflows.
- Define standard procedures for new stakeholders to join and participate in the ecosystem, fostering its future growth and sustainability.

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

Tasks carried out within WP1 consisted in the coordination of all partners, communication with EC and the organization of project meetings. As specific outputs, we defined the project handbook and the data management plans.

For WP2 we worked on different but interrelated tasks. On the one hand, we worked on the definition of the Audio Commons Ontology and released two versions of it (two iterations). On the other hand we worked on the specification of the Audio Commons API and the implementation of the service integration technologies (i.e. the Audio Commons Mediator) which form the basis of the Audio Commons Ecosystem.

In WP3 we have carried out work on describing the intellectual property rights management requirements that arise from the Audio Commons Ecosystem as well as reporting on guidelines about the application of the CC framework in the audio domain. In addition, we explored potential business models for new actors to join the Audio Commons Ecosystem as well as.

Work within work packages WP4 and WP5 has been focused on the development and evaluation of automatic annotation tools for music pieces, music samples and non-musical audio content. As part of the research on these tasks, we reviewed state-of-the-art algorithms for music annotation and developed a hierarchical ontology of timbral attributes for the annotation of non-musical concepts.

Efforts on WP6 have been mainly spent on the development of prototypes by the industrial partners of the consortium. Three working prototypes have already been created which take advantage of Audio Commons technologies.

Finally, work carried out in WP7 consisted in the dissemination activities as described in the dissemination plan. The most important bulk of dissemination so far has been in academic conferences and a number of industrial events.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

A goal of Audio Commons is to make CC audio more easily accessible in existing creative workflows. State-of-the-art for retrieval of CC content reveals problems as content providers have their own APIs, content is not served with unified metadata and tools for retrieving such content barely exist. After M18 of the project, we have already deployed prototype technologies which provide unified access to content from Freesound, Jamendo and Europeana Sounds and allow its easy integration in production applications. Also, we have defined the Audio Commons Ontology which will allow, among other things, the unification of metadata fields. Hence, the work done in AudioCommons already brings some significant improvements beyond the state-of-the-art. By the end of the project, we expect more advanced integration of industry specific tools and CC content. The potential impact of such integrations is huge as it will provide an almost completely new way of sourcing audio content not only for professionals but also for amateurs and individual creators who are in need of audio material.

We identified that one of the main issues that prevent CC licenses to be more extensively used within the creative industries is the unclearness of the licensing procedures. We worked on clarifying these issues by writing documentation which describe the application of CC licenses to the audio domain and by integrating features in the Audio Commons API which facilitate licensing procedures. For example, using the Audio Commons API, a DAW software could integrate a CC browser which once a sound has been downloaded and used could suggest the user to get a license for it and point her to a place to get the license. Even though this by itself is already an improvement over state-of-the-art, after the end of the project we expect that the licensing procedures supported by the Audio Commons API will be more automated. Again, the potential impact of such developments is huge. A clearer way of dealing with CC licenses will facilitate their expansion in commercial applications where single pieces of content (even made even by individual users) could easily be integrated into professional projects. This will foster the use of CC licenses and promote a better collaborative model for media production.

Another important goal of the AudioCommons project is the research and development of tools for the automatic annotation of audio content. These tools will, among other things, allow innovative retrieval methods to be implemented for CC content. In this direction, we already made some small contributions in providing tools that are easy to run and that analyze audio content and output results using terminology from the Audio Commons Ontology. Even if the use of the ontology in the current version of the tools is limited, it is to be expected that it will be increased during the second half of the project. Nevertheless, the specific set of tools that have been developed for the annotation of non-musical properties (i.e. the timbral models), already constitute significant progress beyond state-of-the-art as no

Related information

Follow us on: RSS Facebook Twitter YouTube Managed by the EU Publications Office Top