SAFE [Semantic Audio Feature Extraction] is a joint research project undertaken by the following researchers:

  • Ryan Stables [ryan.stables[at]], Lecturer at the DMT Lab, Birmingham City University, UK.
  • Sean Enderby [sean.enderby[at]], PhD Student at the DMT Lab, Birmingham City University, UK.
  • Brecht De Man [b.deman[at]], PhD Student at the Centre for Digital Music, Queen Mary University of London, UK.
  • Matthew Cheshire [Matthew.Cheshire[at]], PhD Student at the DMT Lab, Birmingham City University, UK.
  • George Fazekas [g.fazekas[at]], Lecturer at the Centre for Digital Music, Queen Mary University of London, UK.

The project is funded in part by the EPSRC Semantic Media Network.

Error Tracking

For things like reporting errors, fixing bugs, requesting features, asking for help and most other enquiries, send an email to: [help[at]] and we’ll get back to you as soon as we can!

For small-ox-related enquiries, please refer to Google.


If you would like to cite the systems or data used in the Semantic Audio project, please use the following citation [pdf | bib]:

R. Stables, S. Enderby, B. De Man, G. Fazekas, and J. D. Reiss, “SAFE: A system for the extraction and retrieval of semantic audio descriptors,”, The International Society for Music Information Retrieval (ISMIR), 2014.