Three experiments in music genre recognition

Add to your list(s) Download to your calendar using vCal

• Bob L. Sturm
• Wednesday 30 May 2012, 12:00-13:00
• Gabor Seminar Room, 611.

If you have a question about this talk, please contact Lauren E Noto.

During the past decade, many researchers have tackled the problem of making computers automatically recognize the genre of recorded music. This is an important problem because it can, among other things, ameliorate the deluge into large databases unlabeled, mislabeled, but always poorly labeled, audio data. The first published work in this area in 2001 achieves a mean accuracy of 61% in ten different genres. Another work from 2006 reaches 83% mean accuracy for this same dataset. And work from 2009 and 2010 claims to observe 91% mean accuracy for this same dataset. With genre so difficult to define, and seemingly based on factors more broad than acoustics, these are remarkable results. In this talk, I argue from results of three simple experiments that the improvements we have seen are unfortunate consequences of excellent discrimination based on confounding factors having little to do with music genre.

Bio:

Bob L. Sturm received in 2009 a Ph.D. degree in Electrical and Computer Engineering at UCSB . Dr. Sturm specializes in signal processing, sparse approximation, and their applications to audio and music. During 2009, Dr. Sturm was a Chateaubriand Post-doctoral Fellow at the Institut Jean Le Rond d’Alembert, Equipe Lutheries, Acoustique, Musique (LAM), at Université Pierre et Marie Curie, Paris 6. In January 2010, Dr. Sturm became Assistant Professor at the Department of Architecture, Design and Media Technology at Aalborg University Copenhagen. In 2011, he was awarded a two-year Independent Postdoc Grant from the Danish Agency for Science, Technology and Innovation, beginning January 2012. His current research interests are: digital signal processing for audio and music signals, algorithms for sparse approximation and compressive sampling, and music and audio information retrieval.

This talk is part of the COMMSP Seminar series.

This talk is included in these lists:

• Andrea Picciau's list
• COMMSP & CP list
• COMMSP Seminar
• Featured talks
• Gabor Seminar Room, 611
• SAP Talks

Note that ex-directory lists are not shown.