Tonic-independent stroke transcription of the mridangam

Akshay Anantapadmanabhan, Juan P. Bello, Raghav Krishnan, Hema A. Murthy

Research output: Chapter in Book/Report/Conference proceedingConference contribution


In this paper, we use a data-driven approach for the tonic-independent transcription of strokes of the mridangam, a South Indian hand drum. We obtain feature vectors that encode tonic-invariance by computing the magnitude spectrum of the constant-Q transform of the audio signal. Then we use Non-negative Matrix Factorization (NMF) to obtain a low-dimensional feature space where mridangam strokes are separable. We make the resulting feature sequence event-synchronous using short-term statistics of feature vectors between onsets, before classifying into a predefined set of stroke labels using Support Vector Machines (SVM). The proposed approach is both more accurate and flexible compared to that of tonic-specific approaches.

Original languageEnglish (US)
Title of host publication53rd AES International Conference 2014
Subtitle of host publicationSemantic Audio
PublisherAudio Engineering Society
Number of pages10
ISBN (Print)9781632662842
StatePublished - 2014
Event53rd AES International Conference 2014: Semantic Audio - London, United Kingdom
Duration: Jan 26 2014Jan 29 2014

Publication series

NameProceedings of the AES International Conference


Other53rd AES International Conference 2014: Semantic Audio
Country/TerritoryUnited Kingdom

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Acoustics and Ultrasonics


Dive into the research topics of 'Tonic-independent stroke transcription of the mridangam'. Together they form a unique fingerprint.

Cite this