Usul and Makam driven automatic melodic segmentation for Turkish music
Open Access
- 3 July 2014
- journal article
- research article
- Published by Taylor & Francis in Journal of New Music Research
- Vol. 43 (4) , 375-389
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.Keywords
This publication has 12 references indexed in Scilit:
- Computational Analysis of Turkish Makam Music: Review of State-of-the-Art and ChallengesJournal of New Music Research, 2014
- Pitch-frequency histogram-based music information retrieval for Turkish musicSignal Processing, 2010
- Melodic Grouping in Music Information Retrieval: New Methods and Applications2010
- Segmentation of Tunisian Modal Improvisation: Comparing Listeners' Responses with Computational PredictionsJournal of New Music Research, 2009
- Motivic Pattern Extraction in Symbolic Domain2008
- Musical Parallelism and Melodic SegmentationMusic Perception: An Interdisciplinary Journal, 2006
- A Comparison of Melodic Segmentation Techniques for Music Information RetrievalLecture Notes in Computer Science, 2005
- Parsing of Melody: Quantification and Testing of the Local Grouping Rules of Lerdahl and Jackendoff's A Generative Theory of Tonal MusicMusic Perception: An Interdisciplinary Journal, 2004
- k-nearest-neighbor Bayes-risk estimationIEEE Transactions on Information Theory, 1975
- Nearest neighbor pattern classificationIEEE Transactions on Information Theory, 1967