Tonic-Independent Stroke Transcription of the Mridangam

Anantapadmanabhan A, Bello J, Krishnan R, Murthy H. Tonic-Independent Stroke Transcription of the Mridangam. In: AES Conference: 53rd International Conference: Semantic Audio. Audio Engineering Society; 2014. Paper P2-2. Available from: https://aes.org/publications/elibrary-page/?id=17102

@inproceedings{Anantapadmanabhan2014_17102,
  author = {Anantapadmanabhan, Akshay and Bello, Juan and Krishnan, Raghav and Murthy, Hema},
  title = {{Tonic-Independent Stroke Transcription of the Mridangam}},
  booktitle = {AES Conference: 53rd International Conference: Semantic Audio},
  note = {Paper P2-2},
  year = {2014},
  month = jan,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=17102}
}

TY  - CPAPER
TI  - Tonic-Independent Stroke Transcription of the Mridangam
AU  - Anantapadmanabhan, Akshay
AU  - Bello, Juan
AU  - Krishnan, Raghav
AU  - Murthy, Hema
T2  - AES Conference: 53rd International Conference: Semantic Audio
M1  - Paper P2-2
PY  - 2014
DA  - 2014/01/06
UR  - https://aes.org/publications/elibrary-page/?id=17102
PB  - Audio Engineering Society
LA  - en
AB  - 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.
ER  -