An optimization-based approach to key segmentation

Ching-Hua Chuan, Elaine Chew

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Keys provide musical context and key modulation (changes) forms a crucial feature of music. In the age of big music data collections, automatic key segmentation is an important step towards music indexing and structure analysis. When using template-based key-finding methods, the best segmentation must minimize intra-segment distance to keys while maximizing inter-segment distance for neighboring keys. We present a general dynamic programming (DP) solution to this segmentation problem that is applicable to all distance-based key-finding methods and that does not require the number of segments to be pre-defined. This metaalgorithm is applied to the Kostka-Payne and Beatles datasets with three widely used distance-based key-finding methods. The key-finding results are evaluated using a compound score, and precision and recall. Statistical analysis of the results show that a precision value of 0.9 can be achieved with both datasets; for excerpts in one key, an average compound score above 0.8 is reported.

Original languageEnglish (US)
Title of host publicationProceedings - 2016 IEEE International Symposium on Multimedia, ISM 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Electronic)9781509045709
StatePublished - Jan 18 2017
Externally publishedYes
Event18th IEEE International Symposium on Multimedia, ISM 2016 - San Jose, United States
Duration: Dec 11 2016Dec 13 2016


Other18th IEEE International Symposium on Multimedia, ISM 2016
Country/TerritoryUnited States
CitySan Jose


  • Correlation
  • Dynamic programming
  • Euclidean distance
  • Key segmentation
  • Kullback-Leibler divergence
  • Tonality

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Media Technology
  • Computer Science Applications


Dive into the research topics of 'An optimization-based approach to key segmentation'. Together they form a unique fingerprint.

Cite this