Automatic Music Summarization. A “Thumbnail” Approach

Downloads

Authors

  • Jakub GŁACZYNSKI Poznan University of Technology Faculty of Computing Science Institute of Computing Science
  • Ewa ŁUKASIK Poznan University of Technology Faculty of Computing Science Institute of Computing Science

Abstract

In the paper, various approaches to automatic music audio summarization are discussed. The project described in detail, is the realization of a method for extracting a music thumbnail – a fragment of continuous music of a given duration time that is most similar to the entire music piece. The results of subjective assessment of the thumbnail choice are presented, where four parameters have been taken into account: clarity (representation of the essence of the piece of music), conciseness (the motifs are not repeated in the summary), coherence of music structure, and overall quality of summary usefulness.

Keywords:

automatic music summarization, music thumbnail, key phrases, automatic music transcription, Music Information Retrieval