Music information retrieval for Turkish music: problems, solutions and tools

Bozkurt, Barış; Gedik, Ali C.; Karaosmanoğlu, M. Kemal

doi:10.1109/siu.2009.5136518

Cited by 5 publications

(6 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The studies that have been accomplished by using sound data utilize alternative features, such as the pitch histogram, harmonic pitch class profiles, etc., which are mainly developed for melodic or tonic analysis. 3,[9][10][11]32 However, we claim that it is the human auditory system that processes the music, regardless of the type of music. Hence, a good simulation of the human auditory system that is valid for Western music must also be valid for Eastern music.…”

Section: Resultsmentioning

confidence: 99%

“…The first group of these studies uses symbolic data, 8, 9,14,18,19 whereas the second group uses audio files. 3,6,7,10–13,16,17 Since our motivation is to build a MIR system, our study is categorized within the second group.…”

Section: Recent Workmentioning

confidence: 99%

“…In another work, a new pitch frequency histogram method for CTM-based MIR problems was proposed. 3 Recently, the same authors offered another solution based on pitch frequency histogram-based features. In this publication, they changed the classifier to a Gaussian Mixture Model (GMM).…”

Section: Recent Workmentioning

confidence: 99%

“…Unlike tonal-based music, makam-based music is not only a function of scales, but also is defined as a combination of the scale and the melodic progression. 1,3 The other important parts of the musical progression of CTM are the seyir (route in Turkish), the ahenk (root frequency of the notes being played), intervals, and composition. The ahenk system is an irregular tuning system that is dependent on the makam, the performer, and even the instrument being played.…”

Section: Introductionmentioning

confidence: 99%

“…The number of semitones differs between 17 and 79, depending on the composer's choice. 3 Moreover, the performer may change the root frequencies of the semitones by his/her own will. In the second half of the 20th century, Arel tried to formalize CTM rules and the tuning system (Arel-Ezgi-Uzgören tuning) based on Pythagorean tuning.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A musical information retrieval system for Classical Turkish Music makams

Kızrak

Bolat

2017

SIMULATION

View full text Add to dashboard Cite

Musical information retrieval (MIR) applications have become an interesting topic both for researchers and commercial applications. The majority of the current knowledge on MIR is based on Western music. However, traditional genres, such as Classical Turkish Music (CTM), have great structural differences compared with Western music. Then, the validity of the current knowledge on this subject must be checked on such genres. Through this work, a MIR application that simulates the human music processing system based on CTM is proposed. To achieve this goal, first mel-frequency cepstral coefficients (MFCCs) and delta-MFCCs, which are the most frequent features used in audio applications, were used as features. In the last few years deep belief networks (DBNs) have become promising classifiers for sound classification problems. To confirm this statement, the classification accuracies of four probability theory-based neural networks, namely radial basis function networks, generalized regression neural networks, probabilistic neural networks, and support vector machines, were compared to the DBN. Our results show that the DBN outperforms the others.

show abstract

Section: Resultsmentioning

confidence: 99%