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.

Authors: Anantapadmanabhan, Akshay; Bello, Juan; Krishnan, Raghav; Murthy, Hema
Affiliations: Indian Institute of Technology Madras, Chennai Tamil Madu, India; New York University, New York, NY, USA(See document for exact affiliation information.)
AES Conference: 53rd International Conference: Semantic Audio (January 2014)
Paper Number: P2-2
Publication Date: January 27, 2014 Import into BibTeX
Subject: Automatic Music Transcription
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=17102

Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!

This paper costs $33 for non-members and is free for AES members and E-Library subscribers.

Learn more about the AES E-Library

E-Library Location: (CD 53rdPapers)   /conf/53/aes53-000058.pdf

Start a discussion about this paper!