Companion webpage for the PhD thesis of Ajay Srinivasamurthy

This page is the companion webpage for the PhD thesis titled

A Data-driven Bayesian Approach to Automatic Rhythm Analysis of Indian Art Music

Ajay Srinivasamurthy

(Last updated: 30 Nov 2016)


Abstract

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.


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.

Peer-reviewed journals

Full articles in peer-reviewed conferences

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.


Meter analysis

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


Audio Features

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)