Projects per year
A recent review of the research literature evaluating music genre recognition (MGR) systems over the past two decades shows that most works (81\%) measure the capacity of a system to recognize genre by its classification accuracy. We show here, by implementing and testing three categorically different state-of-the-art MGR systems, that classification accuracy does not necessarily reflect the capacity of a system to recognize genre in musical signals. We argue that a more comprehensive analysis of behavior at the level of the music is needed to address the problem of MGR, and that measuring classification accuracy obscures the aim of MGR: to select labels indistinguishable from those a person would choose.
|Journal||Journal of Intelligent Information Systems|
|Number of pages||36|
|Publication status||Published - 2013|
FingerprintDive into the research topics of 'Classification Accuracy Is Not Enough: On the Evaluation of Music Genre Recognition Systems'. Together they form a unique fingerprint.
Greedy Sparse Approximation and the Automatic Description of Audio and Music Data
Sturm, B. L.
Technology and Production Independent Postdoc Center for Independent Research
01/01/2012 → …
Christensen, M. G., Tan, Z., Jensen, S. H. & Sturm, B. L.
01/01/2012 → 31/12/2015
- 1 Talks and presentations in private or public companies
The Crisis of Evaluation in Music Information Retrieval
Bob L. Sturm (Lecturer)13 Nov 2013
Activity: Talks and presentations › Talks and presentations in private or public companiesFile