Filter-Based Approach for Ornamentation Detection and Recognition in Singing Folk Music

Andreas Neocleous, George Azzopardi, Christos Schizas, Nikolay Petkov

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

6 Citations (Scopus)


Ornamentations in music play a signicant role for the emo-
tion which a performer or a composer aims to create. The automated
identication of ornamentations enhances the understanding of music,
which can be used as a feature for tasks such as performer identication
or mood classication. Existing methods rely on a pre-processing step
that performs note segmentation. We propose an alternative method
by adapting the existing two-dimensional COSFIRE lter approach to
one-dimension (1D) for the automatic identication of ornamentations
in monophonic folk songs. We construct a set of 1D COSFIRE lters
that are selective for the 12 notes of the Western music theory. The re-
sponse of a 1D COSFIRE lter is computed as the geometric mean of the
dierences between the fundamental frequency values in a local neigh-
bourhood and the preferred values at the corresponding positions. We
apply the proposed 1D COSFIRE lters to the pitch tracks of a song at
every position along the entire signal, which in turn give response values
in the range [0,1]. The 1D COSFIRE lters that we propose are eective
to recognize meaningful musical information which can be transformed
into symbolic representations and used for further analysis. We demon-
strate the eectiveness of the proposed methodology in a new data set
that we introduce, which comprises ve monophonic Cypriot folk tunes
consisting of 428 ornamentations. The proposed method is eective for
the detection and recognition of ornamentations in singing folk music.
Original languageEnglish
Title of host publicationComputer Analysis of Images and Patterns
ISBN (Electronic)978-3-319-23192-1
Publication statusPublished - 2015


  • Signal processing
  • folk music analysis
  • computational ethnomusicology
  • performer classification

Cite this