Audio Commons: an Ecosystem for Creative Reuse of Audio Content

European Commission Horizon 2020 grant ref. 688382

Further information about the project and its partners can be found at www.audiocommons.org

The IoSR researchers contributing to the project are:

Research Fellow: Andy Pearce
Principal Supervisor: Dr Tim Brookes
Co-Supervisor: Dr Russell Mason

Start date: 2016
End date: 2019

Project Outline

The Audio Commons Initiative is aimed at promoting the use of open audio content and at developing technologies with which to support an envisioned ecosystem of content repositories, production tools and users (the Audio Commons Ecosystem). These technologies should enable the reuse of this audio material, facilitating its integration in the production workflows of the creative industries.

The IoSR's role is to determine the categories of timbral attributes most useful to automatic characterisation of sound library elements, and to research, develop and evaluate automatic methods for semantically annotating sound's non-musical characteristics.

Timbral Hierarchy

The first part of this work has identified the timbral attributes that have potential to add value to online audio as automatically-generated tags.

The task was accomplished in two stages. Firstly, a dictionary of timbral attributes and terms used to perceptually describe audio was compiled from the relevant academic literature, and this dictionary was then structured into a hierarchy. Secondly, the frequency of use of each dictionary term, in online searches for audio content, was established in order to give an indication of the potential value of each term; every search within a one month time-frame on Freesound was considered.

This method established that the term deep was the most frequently searched for, followed by dark, soft and electronic. To allow for the fact that a timbral attribute might be labelled using multiple terms, the frequency-of-use for each term was summed into the hierarchical ordering. This showed that the depth attribute (as labelled with the term deep) was only the third most searched for attribute, with the hardness attribute (labelled by hard, pillowy and soft) being the most frequently searched for.

The findings, presented in the associated deliverable document [Pearce et al. 2016], are now guiding our development of automatic tagging tools for timbral attributes.

Publications

Sunburst Plots

Interactive sunburst plots showing the structure of the timbral hierarchy and the terms which comprise each attribute can be found at sunburst.php.

Data Archive

The data generated by this project so far (including code and results) are available in this repository: