Classification accuracy is not enough

@article{Sturm2013ClassificationAI,
  title={Classification accuracy is not enough},
  author={Bob L. Sturm},
  journal={Journal of Intelligent Information Systems},
  year={2013},
  volume={41},
  pages={371-406}
}
We argue that an evaluation of system behavior at the level of the music is required to usefully address the fundamental problems of music genre recognition (MGR), and indeed other tasks of music information retrieval, such as autotagging. A recent review of works in MGR since 1995 shows that most (82 %) measure the capacity of a system to recognize genre by its classification accuracy. After reviewing evaluation in MGR, we show that neither classification accuracy, nor recall and precision… CONTINUE READING
BETA
Tweets
This paper has been referenced on Twitter 3 times. VIEW TWEETS

Citations

Publications citing this paper.
SHOWING 1-10 OF 49 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-10 OF 130 REFERENCES

A survey of evaluation in music genre recognition

  • B. L. Sturm
  • Proc. Adaptive Multimedia Retrieval.
  • 2012
Highly Influential
36 Excerpts

Genre results

  • MIREX
  • http://www.music-ir.org/mirex/wiki/:MIREX_Results…
  • 2005
Highly Influential
4 Excerpts

Similar Papers

Loading similar papers…