Computational Approaches for Melodic Description in Indian Art Music Corpora
This is a companion webpage for the PhD thesis of Sankalp Gulati. All the main resources related with the PhD work (datasets, code, publications, demos etc) are listed in this page.
Short abstract: Automatically describing contents of recorded music is crucial for interacting with large volumes of audio recordings, and for developing novel tools to facilitate music pedagogy. Melody is a fundamental facet in most music traditions and, therefore, is an indispensable component in such description. In this thesis, we develop computational approaches for analyzing high-level melodic aspects of music performances in Indian art music (IAM), with which we can describe and interlink large amounts of audio recordings. With its complex melodic framework and well-grounded theory, the description of IAM melody beyond pitch contours offers a very interesting and challenging research topic. We analyze melodies within their tonal context, identify melodic patterns, compare them both within and across music pieces, and finally, characterize the specific melodic context of IAM, the rāgas. All these analyses are done using data-driven methodologies on sizable curated music corpora. Our work paves the way for addressing several interesting research problems in the field of music information research, as well as developing novel applications in the context of music discovery and music pedagogy.
Full abstract (PDF)
Thesis document (PDF)
PhD defense presentation (Slides, Video)
You can also use/checkout the source files corresponding to the thesis document (see resources tab below). These are the relevant outcomes/resources pertaining to the thesis.
All the datasets used in our work are made publicly available for research purposes. Most of them are version controlled and can be found here. The companion webpages corresponding to the publications list these associated datasets. The prominent ones amongst them are listed below:
Here we list relevant publications related with the work presented in the thesis.
- Gulati, S., Serrà, J., Ganguli, K. K., Şentürk, S., & Serra, X. (2016). Time-delayed melody surfaces for rāga recognition. In Proceedings of the 17th International Society for Music Information Retrieval Conference (ISMIR), pp. 751–757. New York, USA.
- Ganguli, K. K., Gulati, S., Serra, X., & Rao, P. (2016). Data-driven exploration of melodic structures in Hindustani music. In Proceedings of the 17th International Society for Music Information Retrieval Conference (ISMIR), pp. 605-611. New York, USA.
- Gulati, S., Serrà, J., Ishwar, V., Şentürk, S., & Serra, X. (2016). Phrase-based rāga recognition using vector space modeling. In Proceedings of the 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , pp. 66–70. Shanghai, China.
- Gulati, S., Serrà, J., Ishwar, V., & Serra, X. (2016). Discovering rāga motifs by characterizing communities in networks of melodic patterns. In Proceedings of the 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 286–290. Shanghai, China.
- Gulati, S., Serrà, J., & Serra, X. (2015). Improving melodic similarity in Indian art music using culture-specific melodic characteristics. In Proceedings of the 16th International Society for Music Information Retrieval Conference (ISMIR), pp. 680–686. Málaga, Spain.
- Gulati, S., Serrà, J., & Serra, X. (2015). An evaluation of methodologies for melodic similarity in audio recordings of Indian art music. In Proceedings of the 40th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 678–682. Brisbane, Australia.
- Gulati, S., Bellur, A., Salamon, J., Ranjani, H. G., Ishwar, V., Murthy, H. A., & Serra, X. (2014). Automatic tonic identification in Indian art music: approaches and evaluation. Journal of New Music Research, 43(1), 53–71.
- Gulati, S., Serrà, J., Ishwar, V., & Serra, X. (2014). Mining melodic patterns in large audio collections of Indian art music. In Proceedings of the International Conference on Signal Image Technology & Internet Based Systems (SITIS-MIRA), pp. 264–271. Marrakesh, Morocco.
- Gulati, S., Serrà, J., Ganguli, K. K., & Serra, X. (2014). Landmark detection in Hindustani music melodies. In Proceedings of the International Computer Music Conference / Sound and Music Computing Conference (ICMC-SMC), pp. 1062-1068. Athens, Greece.
- Srinivasamurthy, A., Koduri, G. K., Gulati, S., Ishwar, V., & Serra, X. (2014). Corpora for Music Information Research in Indian Art Music. In Proceedings of Joint International Computer Music Conference/Sound and Music Computing Conference, pp. 1029-1036. Athens, Greece.
- Şentürk, S., Gulati, S., & Serra, X. (2014). Towards alignment of score and audio recordings of Ottoman-Turkish makam music. In Proceedings of the 4th International Workshop on Folk Music Analysis (FMA). Istanbul, Turkey.
- Bogdanov, D., Wack, N., Gómez, E., Gulati, S., Herrera, P., Mayor, O., Roma, G., Salamon, J., Zapata, J., & Serra, X. (2013). Essentia: an audio analysis library for music information retrieval. In Proceedings of the 14th International Society for Music Information Retrieval Conference (ISMIR), pp. 493–498. Curitiba, Brazil.
- Bogdanov, D., Wack, N., Gómez, E., Gulati, S., Herrera, P., Mayor, O., Roma, G., Salamon, J., Zapata, J., & Serra, X. (2013). ESSENTIA: an open-source library for sound and music analysis. In Proceedings of the 21st ACM international conference on Multimedia, pp. 855–858. Barcelona, Spain.
- Şentürk, S., Gulati, S., & Serra, X. (2013). Score informed tonic identification for makam music of Turkey. In Proceedings of the 14th International Society for Music Information Retrieval Conference (ISMIR), pp. 175–180. Curitiba, Brazil.
- 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 the 2nd CompMusic Workshop. Istanbul, Turkey.
- Koduri, G. K., Gulati, S., Rao, P., & Serra, X. (2012). Rāga recognition based on pitch distribution methods. Journal of New Music Research, 41(4), 337–350.
- Koduri, G. K., Gulati, S., & Rao, P. (2011). A survey of raaga recognition techniques and improvements to the state-of-the-art. In Proceedings of the Sound and Music Computing Conference (SMC). Padova, Italy.
The core code corresponding to the experiments performed as a part of the thesis is organized in single git repository. The specific wrappers for individual experiments are also version controlled and can be found here. Links to specific selected scripts/code are given below.
-
Nyās segmentation and classification [Python]
-
Predominant pitch post-processing [Python]
-
Tani Segmentation [Python]
-
Pattern processing: melodic similarity, and pattern search and discovery (including cascaded lower-bound computations) [C]
-
DTW variants [C, Python-wrapper]
-
Melodic pattern characterization [Python]
-
The core code corresponding to the
Rāga recognition using TDMS [Python]
-
Pitch estimation using the YIN algorithm [JavaScript]
The code for the individual experiments needs refactoring. It will be done soon..untill then if there is any confusion please feel free to contact the author.
The majority of the results of my work (tonic identification, nyas segmentation, raga recognition etc.) are single labels/numbers for each audio recording, the results of which are summarized in the respective publications. The results of some of the studies (pattern discovery for example) are also made available in the form of web-based demos. These are summarized below.
- Pattern discovery output organized according to editorial metadata. It can be accessed from here. This interface is good to browse patterns of a particular artists from a particular recording/work.
- Pattern discovery output organized as a network of patterns. It can be accessed from here. This interface is good to highlight relations across different recordings, artists or ragas.
- Ragawise: a web-based interface for demonstrating a real-time raga recognition system.
A number of results/outcome of the thesis work are already incorporated in mobile applications that are designed to provide enhance listening experience of Indian art music and as a tool to aid in learning and teaching of this music tradition. The particular applications are given below.
- Sarāga: A mobile application that provides an enriched listening atmosphere over a collection of Carnatic and Hindustani music.
- Riyāz: A mobile application that aims to facilitate music learning for students of Indian art music by making their practice sessions more efficient.
Apart from these results, certain outcomes of my work are also integrated into Dunya. These features are available from both the Dunya webpage as well as through Dunya API.
- Essentia feature extraction library
- PyCompMusic (Python wrapper around Dunya API)
- CompMusic Dunya platform
- Dunya web-front end
There might be several resources related with the PhD thesis document (*.bib, glossaries, figures, tables etc) that might be of use. The source files I used to generate the thesis document are shared here (github). Before you use any material please carefully go through the license (CC-By-NC-ND 4.0). If you wish to remix, transform or build upon this material and share the modified version, please contact the author (sankalp.gulati gmail com).