eduzhai > Applied Sciences > Engineering >

A Computational Analysis of Real-World DJ Mixes using Mix-To-Track Subsequence Alignment

  • king
  • (0) Download
  • 20210507
  • Save

... pages left unread,continue reading

Document pages: 7 pages

Abstract: A DJ mix is a sequence of music tracks concatenated seamlessly, typicallyrendered for audiences in a live setting by a DJ on stage. As a DJ mix isproduced in a studio or the live version is recorded for music streamingservices, computational methods to analyze DJ mixes, for example, extractingtrack information or understanding DJ techniques, have drawn researchinterests. Many of previous works are, however, limited to identifyingindividual tracks in a mix or segmenting it, and the sizes of the datasets areusually small. In this paper, we provide an in-depth analysis of DJ music byaligning a mix to its original music tracks. We set up the subsequencealignment such that the audio features are less sensitive to the tempo or keychange of the original track in a mix. This approach provides temporally tightmix-to-track matching from which we can obtain cue-points, transition length,mix segmentation, and musical changes in DJ performance. Using 1,557 mixes from1001Tracklists including 13,728 tracks and 20,765 transitions, we conduct theproposed analysis and show a wide range of statistics, which may elucidate thecreative process of DJ music making.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...