This is a work in progress. We would like to invite you to sign in and contribute.
SOVARR is a community-oriented project that aims to examine possibilities of creating a shared representation of audio features within research communities.
Researchers in audio (including speech, music, bioacoustics and environmental audio signal processing and retrieval) increasingly use a common set of feature extraction techniques to characterise audio material, while large data sets of features are commonly released for public and scientific use. The development of data sets and research tools however are not governed by shared open vocabularies and common data structures. Instead, they typically rely on ad-hoc file formats and information management solutions, chosen without considering sustainability and research reproducibility. This raises several issues, including
- the need for adapting research code and research environments for a variety of different formats,
- the difficulty of combining similar data sets from different sources to form larger data sets,
- the difficulty of using complementary datasets together, and
- the lack of interoperability between research tools.
The main objectives of this project are to:
- investigate the extent to which an agreement on the representation of audio features can be be reached within research communities
- review current tools and literature
- involve the related research communities in the discussion
- update existing research tools and ontologies
- deliver workshops and tutorials focusing on the benefits of using a shared open vocabulary
More detailed information about the project, including a blog on current updates and news, can be found on the SOVARR website.
Structure of the wiki
- Audio features
- Existing research tools and vocabularies
- Requirements specification
- Ontology engineering
- The Audio Feature Ontology Framework
- Documents and publications