A Cross-Scape Plot Representation for Visualizing Symbolic Melodic Similarity

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 214
  • Download : 0
Symbolic melodic similarity is based on measuring a pairwise distance between two songs from diverse perspectives. The distance is usually summarized as a single value for song retrieval. This obscures observing the details of similarity patterns within the two songs. In this paper, we propose a cross-scape plot representation to visualize multi-scaled melody similarity between two symbolic music encodings. The cross-scape plot is computed by stacking up a minimum local distance between two segments from each of the two songs. As the layer goes up, the segment size increases and it computes incrementally more long-term distances. This hierarchical representation allows for capturing the location and length of similar segments between two songs in a visually intuitive manner. We show the effectiveness of the cross-scape plot by evaluating it on examples from folk music collections with similarity-based categories and plagiarism cases.
Publisher
International Society for Music Information Retrieval Conference (ISMIR)
Issue Date
2019-11-04
Language
English
Citation

The 20th International Society for Music Information Retrieval Conference (ISMIR), pp.423 - 430

URI
http://hdl.handle.net/10203/269875
Appears in Collection
GCT-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0