The SoundSoftware.ac.uk Prizes for Reproducibility in Audio and Music Research have been announced.
I am happy to report that some of my works (with collaborators F. Gouyon and P. Noorzad) are among them.
In particular, our prize (supporting the open-access publication of a journal article) was awarded for the following three items:
- B. L. Sturm and F. Gouyon, “Revisiting Inter-Genre Similarity”, submitted Mar. 2013, resubmitted June 2013. MATLAB code is here. This paper resolves some contradictions posed by the results published in: U. Bagci and E. Erzin, “Automatic classification of musical genres using inter-genre similarity,” IEEE Signal Processing Letters, vol. 14, no. 8, pp. 521-524, Aug. 2007.
- B. L. Sturm, “On music genre classification via compressive sampling“, Proc. IEEE Int. Conf. Multimedia & Expo, July 2013. MATLAB code is here. This paper resolves some contradictions posed by the results published in: K. Chang, J.-S. R. Jang, and C. S. Iliopoulos, “Music genre classification via compressive sampling,” in Proc. ISMIR, (Amsterdam, The Netherlands), pp. 387-392, Aug. 2010.
- B. L. Sturm and P. Noorzad, “On Automatic Music Genre Recognition by Sparse Representation Classification using Auditory Temporal Modulations“, Proc. Computer Music Modeling and Retrieval, QMUL, London, UK, June 2012. MATLAB code is here. This paper attempts to reproduce the results published in: Y. Panagakis, C. Kotropoulos, and G. R. Arce, “Music genre classification via sparse representations of auditory temporal modulations,” in Proc. EUSIPCO, Aug. 2009.
There are other awarded works there that appear quite interesting to me. I look forward to
- Giannoulis, D., Stowell, D., Benetos, E., Rossignol, M., Lagrange, M., and Plumbley, M. D., “A Database and Challenge for Acoustic Scene Classification and Event Detection”, conference submission.
- Raffel, C., and Ellis, D., Reproducing Pitch Experiments in “Measuring the Evolution of Contemporary Western Popular Music”, technical report.
Thank you to the organizers of this prize! It is a great way to motivate reproducibility in disciplines that suffer from a lack of transparency.