Şentürk, S. (2016). Computational analysis of audio recordings and music scores for the description and discovery of Ottoman-Turkish makam music. PhD thesis, Universitat Pompeu Fabra, Barcelona, Spain.
(the thesis and the presentation will be uploaded after the defense on 22 February 2017)
Quick Access > Music Examples – Research Corpus – Test Datasets – Code – Results – Publications – Licenses
This thesis addresses several shortcomings of the current state of the art methodologies in music information retrieval (MIR). In particular, it proposes several computational approaches to automatically analyze and describe music scores and audio recordings of Ottoman–Turkish makam music (OTMM). The main contributions of the thesis are the music corpus that has been created to carry out the research and the audio-score alignment methodology developed for the analysis of the corpus. In addition, several novel computational analysis methodologies are presented in the context of common MIR tasks of relevance for OTMM. Some example tasks are predominant melody extraction, tonic identification, tempo estimation, makam recognition, tuning analysis, structural analysis and melodic progression analysis.
The analysis methodologies presented in the thesis are applied to the CompMusic Ottoman–Turkish makam music corpus, which includes 2200 music scores, more than 6500 audio recordings, and accompanying metadata. The corpus and these methodologies become a part of a complete system called Dunya-makam for the exploration of large corpora of OTMM. In addition, some of the methodologies have already been applied to other music traditions such as Hindustani, Carnatic and Greek music. Following open research best practices, all the created data, software tools, and analysis results are openly available. The methodologies, the tools and the corpus itself provide vast opportunities for future research in many fields such as music information retrieval, computational musicology, and music education.
1. Music Examples
These examples are compiled to show the main challenges faced in the computational analysis of OTMM such as tuning, intonation, heterophony in the performances and descriptiveness of the music scores. You have to register to Dunya-makam to listen to the audio recordings. For a thorough explanation, please refer to Chapter 2 of the thesis.
- Hüseyni Peşrev by Lavtacı Andon
- Muhayyer Sazsemaisi by Tanburi Cemil Bey
2. Research Corpus
The CompMusic Ottoman-Turkish makam music (OTMM) corpus consists of the audio recordings, music scores, metadata related to these information sources and automatic description extracted from the corpus itself. The data can be accessed from the Dunya API. The API documentation is online at:
The music scores in the corpus are taken from the SymbTr music score collection. The collection is maintained at:
The metadata is hosted in MusicBrainz and organized into several collections:
- Ottoman-Turkish makam: The releases in the CompMusic OTMM audio collection
- Ottoman-Turkish makam excluded: The “unrepresentative” releases in the CompMusic OTMM audio collection
- Dunya Ottoman-Turkish makam stream: The audio recordings, which we have obtained the rights to stream in Dunya
- SymbTr music score collection: The works related to the music scores in the SymbTr collection
3. Test Datasets
I have created numerous test datasets during my doctoral research:
- OTMM Symbolic Section Dataset
- OTMM Makam Recognition Dataset
- OTMM Tonic Identification Datasets
- OTMM Composition Identification Dataset
- OTMM Section Linking Dataset
- OTMM Partial Audio-Score Alignment Dataset
- OTMM Audio-Score Alignment Dataset
I have assisted the creation of two audio-lyrics alignment datasets:
In addition, I used several datasets created by other members of CompMusic project:
- OTMM Symbolic Melodic Segmentation Dataset
- Carnatic Varnam Dataset
- Carnatic Kriti Dataset
- Indian Art Music Raga Recognition Dataset
The implementations of the methodologies proposed to analyze the audio recordings and music scores (Chapters 4-6) are part of Turkish-Ottoman Makam (M)usic Analysis TOolbox (tomato). In addition, tomato contains the tools to convert the SymbTr music scores to MusicXML, LilyPond and SVG formats. The toolbox is open at:
Some complementary software tools used in the thesis are:
- Essentia audio feature extraction library
- Dunya-web platform
- pycompmusic, a Python wrapper around Dunya-web API
- Dunya-desktop, an extendable desktop interface for the navigation and annotation of music data
The automatic description of the CompMusic OTMM corpus is open and available via the Dunya website. The data can be obtained using, a Python wrapper around the Dunya API.
The metadata and the automatic description are used in a web application aimed at the discovery of the CompMusic OTMM corpus. It allows the users to navigate the audio collection and play the audio recordings synchronous to the automatic description. The application is hosted in Dunya-web at:
A list of my academic publications, organized by the relevance to the thesis is presented below. An up-to-date list of my publications can be found at the page:
Articles in peer-reviewed journals
- Şentürk, S., Holzapfel, A., & Serra, X. (2014). Linking scores and audio recordings in makam music of Turkey. Journal of New Music Research, 43:34–52.
Papers published in peer-reviewed conferences
- Şentürk, S., & Serra X. (2016). Composition Identification in Ottoman-Turkish Makam Music Using Transposition-Invariant Partial Audio-Score Alignment. In Proceedings of 13th Sound and Music Computing Conference (SMC 2016). pages 434–441, Hamburg, Germany
- Şentürk, S., Koduri G. K., & Serra X. (2016). A Score-Informed Computational Description of Svaras Using a Statistical Model. In Proceedings of 13th Sound and Music Computing Conference (SMC 2016). pages 427–433, Hamburg, Germany
- Karakurt, A., Şentürk S., & Serra X. (2016). MORTY: A Toolbox for Mode Recognition and Tonic Identification. In Proceedings of 3rd International Digital Libraries for Musicology Workshop (DLfM 2016). pages 9–16, New York, NY, USA.
- Gulati, S., Serrà J., Ganguli K. K., Şentürk S., & Serra X. (2016). Time-Delayed Melody Surfaces for Rāga Recognition. In Proceedings of 17th International Society for Music Information Retrieval Conference (ISMIR 2016), pages 751–757, New York, NY, USA
- Şentürk S., & Serra X. (2016). A method for structural analysis of Ottoman-Turkish makam music scores. In Proceedings of 6th International Workshop on Folk Music Analysis (FMA 2016), pages 39–46, Dublin, Ireland
- Gulati, S., Serrà J., Ishwar V., Şentürk S., & Serra X. (2016). Phrase-based Rāga Recognition Using Vector Space Modeling. In Proceedings of 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), pages 66–70, Shanghai, China
- Şentürk, S., Ferraro, A., Porter, A., & Serra, X. (2015). A tool for the analysis and discovery of Ottoman-Turkish makam music. In Extended Abstracts for the Late Breaking Demo Session of the 16th International Society for Music Information Retrieval Conference (ISMIR 2015), Málaga, Spain, 2015
- Atlı, H. S., Bozkurt, B., Şentürk, S. (2015). A Method for Tonic Frequency Identification of Turkish Makam Music Recordings. In Proceedings of 5th International Workshop on Folk Music Analysis (FMA 2015), pages 119&ndash122, Paris, France.
- Holzapfel, A., Şimşekli U., Şentürk S., & Cemgil A. T. (2015). Section-level Modeling of Musical Audio for Linking Performances to Scores in Turkish Makam Music. In Proceedings of 40th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2015), pages 141–145, Brisbane, Australia.
- Atlı, H. S., Uyar, B., Şentürk, S., Bozkurt, B., & Serra, X. (2015). Audio feature extraction for exploring Turkish makam music. In Proceedings of 3rd International Conference on Audio Technologies for Music and Media (ATMM 2015), pages 142–153, Ankara, Turkey.
- Uyar, B., Atlı, H. S., Şentürk, S., Bozkurt, B., & Serra, X. (2014). A corpus for computational research of Turkish makam music. In Proceedings of 1st International Digital Libraries for Musicology Workshop (DLfM 2014), pages 57–63, London, United Kingdom.
- Şentürk, S., Gulati, S., & Serra, X. (2014). Towards alignment of score and audio recordings of Ottoman-Turkish makam music. In Proceedings of 4th International Workshop on Folk Music Analysis (FMA 2014), pages 57–60, Istanbul, Turkey.
- Şentürk, S., Gulati, S., & Serra, X. (2013). Score informed tonic identification for makam music of Turkey. In Proceedings of 14th International Society for Music Information Retrieval Conference (ISMIR 2013), pages 175–180, Curitiba, Brazil.
Şentürk, S., Holzapfel, A., & Serra, X. (2012). An approach for linking score and audio recordings in makam music of Turkey. In Proceedings of 2nd CompMusic Workshop, pages 95–106, Istanbul, Turkey.
- Sordo, M., Koduri, G. K., Şentürk, S., Gulati, S., & Serra, X. (2012). A musically aware system for browsing and interacting with audio music collections. In Proceedings of 2nd CompMusic Workshop, pages 20–24, Istanbul, Turkey.
Publications within the CompMusic project, which are outside the context of the thesis
- Dzhambazov, G., Srinivasamurthy A., Şentürk S., & Serra X. (2016). On the Use of Note Onsets for Improved Lyrics-to-audio Alignment in Turkish Makam Music. In Proceedings of 17th International Society for Music Information Retrieval Conference (ISMIR 2016), pages 716–722, New York, NY, USA
- Dzhambazov, G., Şentürk, S., & Serra, X. (2015). Searching lyrical phrases in a-capella Turkish makam recordings. In Proceedings of 16th International Society for Music Information Retrieval Conference (ISMIR 2015), pages 687–693, Málaga, Spain
- Atıcı, M., Bozkurt, B., Şentürk, S. (2015). A Culture-Specific Analysis Software for Makam Music Traditions. In Proceedings of 5th International Workshop on Folk Music Analysis (FMA 2015), pages 88–96, Paris, France.
- Dzhambazov, G., Şentürk, S., & Serra, X. (2014). Automatic lyrics-to-audio alignment in classical Turkish music. In Proceedings of 4th International Workshop on Folk Music Analysis (FMA 2014), pages 61–64, Istanbul, Turkey.
Relevant publications outside the CompMusic project
- Chordia, P., & Şentürk, S. (2013). Joint recognition of raag and tonic in North Indian music. Computer Music Journal, 37(3):82–98.
- Chordia, P., Sastry, A., & Şentürk, S. (2011). Predictive tabla modelling using variable-length Markov and hidden Markov models. Journal of New Music Research, 40(2):105–118.
- Şentürk, S. (2011). Computational modeling of improvisation in Turkish folk music using variable-length Markov models. Master’s thesis, Georgia Institute of Technology, Atlanta, GA, USA.
- Şentürk, S., & Chordia, P. (2011). Modeling melodic improvisation in Turkish folk music using variable-length Markov models. In Proceedings of 12th International Society for Music Information Retrieval Conference (ISMIR 2011), pages 269–274, Miami, FL, USA.
Other academic publications outside CompMusic project
- Şentürk, S., Lee, S. W., Sastry, A., Daruwalla, A., & Weinberg, G. (2012). Crossole: A gestural interface for composition, improvisation and performance using Kinect. In Proceedings of International Conference on New Interfaces for Musical Expression (NIME 2012), pages 449–502, Ann Arbor, MI, USA.
- Albin, A., Şentürk, S., Van Troyer, A., Blosser, B., Jan, O., & Weinberg, G. (2011). Beatscape, a mixed virtual-physical environment for musical ensembles. In Proceedings of International Conference on New Interfaces for Musical Expression (NIME 2011), pages 112–115, Oslo, Norway.
- Kocyigit, F. B., & Senturk, S. (2008). Acoustics in the partial deaf student school music classrooms. In Proceedings of Acoustics’08 Paris Conference, pages 3919–3924, Paris, France.
- Şentürk, S. (2013). Sesin Özgürleşmesi: Müzik Prodüksiyonu Teknolojileri. Birikim Dergisi, 285:98–104.
- Şentürk, S. (2011). Interactivity in Contemporary Dance and Music. Self Published.
All the code presented in the thesis is licensed under GNU Affero General Public License Version 3 unless stated otherwise.
All the data (e.g. the music scores, extracted features, training models, figures, text, outputs) except the copyrighted material (e.g. commercial recordings) are licensed under Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License unless stated otherwise.