This page is the companion webpage for the PhD thesis titled
A Data-driven Bayesian Approach to Automatic Rhythm Analysis of Indian Art Music
(Last updated: 30 Nov 2016)
Large and growing collections of a wide variety of music are now available on demand to music listeners, necessitating novel ways of automatically structuring these collections using different dimensions of music. Rhythm is one of the basic music dimensions and its automatic analysis, which aims to extract musically meaningful rhythm related information from music, is a core task in Music Information Research (MIR). The thesis aims to build data-driven signal processing and machine learning approaches for automatic analysis, description and discovery of rhythmic structures and patterns in audio music collections of Indian art music. After identifying challenges and opportunities, we present several relevant research tasks that open up the field of automatic rhythm analysis of Indian art music. Data-driven approaches require well curated data corpora for research and efforts towards creating such corpora and datasets are documented in detail. We then focus on the topics of meter analysis and percussion pattern discovery in Indian art music. The data and tools should be relevant for data-driven musicological studies and other MIR tasks that can benefit from automatic rhythm analysis.
A longer and detailed abstract is here: http://mtg.upf.edu/node/3593
Link to the thesis document
Link to the thesis defense presentation slides
Please click on the headings to expand.
- A resource page for Carnatic tāḷas
- A resource page for Hindustani tāls
- A resource page for Turkish usuls
- Percussion instruments used in Beijing opera
- Percussion patterns in Beijing opera
All the datasets built within CompMusic can be found here: http://compmusic.upf.edu/datasets
Some of the datasets more extensively used in the thesis are linked below:
- Carnatic Music Rhythm (CMR) dataset
- Hindustani Music Rhythm (HMR) dataset
- Mulgaonkar Tabla Solo (MTS) dataset
- UKS Mridangam Solo (UMS) dataset
- Jingju Percussion Instrument (JPI) dataset
- Jingju Percussion Pattern (JPP) dataset
The following is a list of publications by the author in the context of the thesis and CompMusic project. The title of the papers link to the companion page of each paper that contains additional information.
- Srinivasamurthy, A., Holzapfel, A., & Serra, X. (2014). In Search of Automatic Rhythm Analysis Methods for Turkish and Indian Art Music. Journal of New Music Research, 43(1), 97–117.
Full articles in peer-reviewed conferences
- Srinivasamurthy, A., Holzapfel, A., Cemgil, A. T., & Serra, X. (2016, March). A generalized Bayesian model for tracking long metrical cycles in acoustic music signals. In Proceedings of the 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016) (pp. 76–80). Shanghai, China.
- Srinivasamurthy, A., Holzapfel, A., Cemgil, A. T., & Serra, X. (2015, October). Particle Filters for Efficient Meter Tracking with Dynamic Bayesian Networks. In Proceedings of the 16th International Society for Music Information Retrieval Conference (ISMIR 2015) (pp. 197–203). Malaga, Spain.
- Gupta, S., Srinivasamurthy, A., Kumar, M., Murthy, H., & Serra, X. (2015, October). Discovery of Syllabic Percussion Patterns in Tabla Solo Recordings. In Proceedings of the 16th International Society for Music Information Retrieval Conference (ISMIR 2015) (pp. 385–391). Malaga, Spain.
- Srinivasamurthy, A., Caro, R., Sundar, H., & Serra, X. (2014, October). Transcription and Recognition of Syllable based Percussion Patterns: The Case of Beijing Opera. In Proceedings of the 15th International Society for Music Information Retrieval Conference (ISMIR 2014) (pp. 431–436). Taipei, Taiwan.
- Holzapfel, A., Krebs, F., & Srinivasamurthy, A. (2014, October). Tracking the "odd": Meter inference in a culturally diverse music corpus. In Proceedings of the 15th International Society for Music Information Retrieval Conference (ISMIR 2014) (pp. 425–430). Taipei, Taiwan.
- Srinivasamurthy, A., Koduri, G. K., Gulati, S., Ishwar, V., & Serra, X. (2014, September). Corpora for Music Information Research in Indian Art Music. In Proceedings of Joint International Computer Music Conference/Sound and Music Computing Conference. Athens, Greece.
- Srinivasamurthy, A., & Serra, X. (2014, May). A Supervised Approach to Hierarchical Metrical Cycle Tracking from Audio Music Recordings. In Proceedings of the 39th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014) (pp. 5237–5241). Florence, Italy.
- Tian, M., Srinivasamurthy, A., Sandler, M., & Serra, X. (2014, May). A Study of Instrument-wise Onset Detection in Beijing Opera Percussion Ensembles. In Proceedings of the 39th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014) (pp. 2174–2178). Florence, Italy.
- Srinivasamurthy, A., Subramanian, S., Tronel, G., & Chordia, P. (2012, July). A Beat Tracking Approach to Complete Description of Rhythm in Indian Classical Music. In Proceedings of the 2nd CompMusic Workshop (pp. 72–78). Istanbul, Turkey.
Other contributions to conferences
- Krebs, F., Holzapfel, A., & Srinivasamurthy, A. (2014). MIREX 2014 Audio Downbeat Tracking Evaluation: KHS1. 10th Music Information Retrieval Evaluation eXchange (MIREX), extended abstract. Taipei, Taiwan.
- Gulati, S., Ganguli, K. K., Gupta, S., Srinivasamurthy, A., & Serra, X. (2015). RAGAWISE: A Lightweight Real-time Raga Recognition System for Indian Art Music. In Late-Breaking Demo Session of the 16th International Society for Music Information Retrieval Conference. Malaga, Spain.
- Caro, R., Srinivasamurthy, A., Gulati, S., & Serra, X. (2014). Jingju music: Concepts and Computational Tools for its Analysis. A Tutorial in the 15th International Society for Music Information Retrieval Conference, Taipei, Taiwan.
- Essentia audio analysis library: http://essentia.upf.edu/
- Dunya API: https://github.com/MTG/pycompmusic
- Dunya server and back end: https://github.com/MTG/dunya
- A MATLAB package for meter analysis (maintained by Florian Krebs): https://github.com/flokadillo/bayesbeat
- A MATLAB/Python package for percussion pattern transcription using the HTK and RLCS: https://github.com/swapnilgt/percPatternDiscovery
- A MATLAB package for beat tracking evaluation (maintained by Matthew Davies): https://code.soundsoftware.ac.uk/projects/beat-evaluation/
- Rhythm analysis tools for jingju, from the tutorial in ISMIR 2014: http://compmusic.upf.edu/jingju-tutorial
- Sawaal-Jawaab Code and Demo: http://compmusic.upf.edu/ismir-15-hacks
- BeatStation, an interface to record beat tapping (first developed by Marius Miron, extension to Carnatic music by Ajay Srinivasamurthy): https://github.com/ajaysmurthy/beatStation
Some audio examples of meter analysis are here: http://dunya.compmusic.upf.edu/ajay-thesis/examplesPage.htm
Percussion pattern discovery
Some audio examples of percussion pattern discovery are here (examples generated with the help of Swapnil Gupta): http://dunya.compmusic.upf.edu/ajay-thesis/tablaExamples.htm
The examples below are a sonification of the spectral flux using a sawtooth signal of 800Hz with an amplitude envelope of the spectral flux feature used in the thesis. An audible click is also present at the true location of the sama (downbeat). The tracks are stereo: left and right channels have the spectral flux from low and high frequency bands, respectively.
Brochevarevarura in adi tala (MusicBrainz)
Sri Mahaganapati in mishra chapu tala (MusicBrainz)
(The page http://www.ajaysrinivasamurthy.in/phd-thesis redirects to this page)