Composition Identification in Ottoman-Turkish Makam Music Using Transposition-Invariant Partial Audio-Score Alignment

TitleComposition Identification in Ottoman-Turkish Makam Music Using Transposition-Invariant Partial Audio-Score Alignment
Publication TypeConference Paper
Year of Publication2016
Conference Name13th Sound and Music Computing Conference (SMC 2016)
AuthorsŞentürk, S., & Serra X.
Pagination434-441
Conference Start Date31/08/2016
PublisherZentrum für Mikrotonale Musik und Multimediale Komposition (ZM4) Hochschule für Musik und Theater
Conference LocationHamburg, Germany
AbstractThe composition information of audio recordings is highly valuable for many tasks such as automatic music description and music discovery. Given a music collection, two typical scenarios are retrieving the composition(s) performed in an audio recording and retrieving the audio recording(s), where a composition is performed. We present a composition identification methodology for these two tasks, which makes use of music scores. Our methodology first attempts to align a fragment of the music score of a composition with an audio recording. Next, it computes a similarity from the best obtained alignment. True audio-score pair emits a high similarity value. We repeat this procedure between all audio recordings and music scores, and filter the true pairs by a simple approach using logistic regression. The methodology is specialized according to the cultural-specific aspects of Ottoman-Turkish makam music (OTMM), achieving 0.96 and 0.95 mean average precision (MAP) for composition retrieval and performance retrieval tasks, respectively. We hope that our method would be useful in creating semantically linked music corpora for cultural heritage and preservation, semantic web applications and musicological studies.
Additional material: 

Musical Examples

These examples are compiled to show the readers the main challenges faced in the composition identification task applied on 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 Section 2 in the paper.

  1. Hüseyni Peşrev by Lavtacı Andon
  2. Muhayyer Sazsemaisi by Tanburi Cemil Bey

Dataset

The dataset consist of 743 audio recordings and 147 music scores of different compositions. All the relevant metadata is entered and hosted in MusicBrainz. You can access the dataset via github. Please refer to Section 3 in the paper for the statistics of the dataset.

Code

The original code is written in MATLAB. We are currently porting it to Python to integrate it to our Ottoman-Turkish makam music analysis toolbox. In the meantime, please contact the authors to obtain the original MATLAB code.

Results

The complete results can be downloaded from ZenodoThe results and its discussion are given in detail in Sections 7 and 8.

intranet