Melody extraction on MIDI music files

Creative Commons License

Ozcan G., Işıkhan C., Alpkoçak A.

7th IEEE International Symposium on Multimedia, Irvine, United Kingdom, 12 - 14 December 2005, pp.414-421 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/ism.2005.77
  • City: Irvine
  • Country: United Kingdom
  • Page Numbers: pp.414-421
  • Keywords: Melody Extraction, pitch histogram, Music Information Retrieval
  • Dokuz Eylül University Affiliated: Yes


In this study, we propose a new, approach to extract monophonic melody from MIDI files and provide a comparison of existing methods. Our approach is based on the elimination of MIDI channels those do not contain Inelodic information. First, MIDI channels are clustered depending on pitch histogram. Afterwards, a channel is selected from each cluster as representative and remaining, channels and their notes am, removed Finally, Skyline algorithm is applied on the modified MIDI set to ensure accuracy of monophonic melody. We evaluated our approach within a test bed of MIDI files, composed of variable music styles. Both our approach and the results from experiments are presented in detail.