Usul and Makam driven automatic melodic segmentation for Turkish music

Abstract

Automatic melodic segmentation is a topic studied extensively, aiming at developing systems that perform grouping of musical events. Here, we consider the problem of automatic segmentation via supervised learning from a dataset containing segmentation labels of an expert. We present a statistical classification-based segmentation system developed specifically for Turkish makam music. The proposed system uses two novel features, a makam-based and an usul-based feature, together with features commonly used in literature. The makam-based feature is defined as the probability of a note to appear at the phrase boundary, computed from the distributions of boundaries with respect to the piece's makam pitches. Likewise, the usul-based feature is computed from the distributions of boundaries with respect to beats in the rhythmic cycle, usul of the piece. Several experimental setups using different feature groups are designed to test the contribution of the proposed features on three datasets. The results show that the new features carry complementary information to existing features in the literature within the Turkish makam music segmentation context and that the inclusion of new features resulted in statistically significant performance improvement.

A Corpus for Computational Research of Turkish Makam Music

“…The corpus is created under the considerations to meet some criteria: purpose, quality, completeness, coverage and re-usability. We also present some test datasets, which have been used to test and calibrate some computational tasks [6,7,14,15,16]. We hope that this research corpus and the test datasets will facilitate academic studies in several fields such as music information retrieval and computational musicology.…”

“…Karaosmanoglu and Bozkurt have studied the problem of usul and makam driven automatic melodic segmentation for Turkish Music [6]. For this research, 899 SymbTr-scores were manually annotated into melodic segments by 3 experts.…”

Unsupervised Symbolic Music Segmentation using Ensemble Temporal Prediction Errors

“…The task of music segmentation is made more difficult by the fact that there is more than a single possible segmentation solution. Certain boundaries can be subjective or ambiguous, a fact demonstrated by multiple researchers who have compared music segmentations of both listeners and musicians [3,4,5,6,7].…”