TablaNet: a Real-Time Online Musical Collaboration System for Indian Percussion

“I am learning to play the Indian tabla drums in my village, but my teacher lives in a far-away town and I cannot meet him regularly.” This plight of a rural student illustrates the need for software that "understands" rhythmic patterns in order to adequately represent and efficiently transmit the musical signal over the Internet. However real-time online collaboration is constrained by the latency of networks which introduce time delays unsuitable for musical applications. In this context, we create a system based on pattern recognition and music prediction. Trained for a particular type of music, here the Indian tabla drum, our system recognizes individual drum strokes at one end, extracts high level musical features such as pitch and tempo, identifies rhythmic phrases, and transmits these musical structures over the network. At the receiving end, our system anticipates incoming events by analyzing previous phrases, and synthesizes an estimated audio output.

Publications

M. Sarkar, “TablaNet: a Real-Time Online Musical Collaboration System for Indian Percussion”, master's thesis, Massachusetts Institute of Technology (MIT), Cambridge, Mass., USA, Aug. 2007.

M. Sarkar, B. Vercoe, “Recognition and Prediction in a Network Music Performance System for Indian Percussion,” International Conference on New Interfaces for Musical Expression (NIME 2007), New York, NY, USA, June 6-9, 2007.

M. Sarkar, “TablaNet: a Real-Time Online Musical Collaboration System for Indian Percussion”, unpublished thesis proposal, MIT Media Lab, Cambridge, Mass., USA, Dec. 2006.

M. Sarkar, “Tabla Strokes Recognition”, unpublished project presentation, MAS.622, MIT, Cambridge, Mass., USA, Dec. 2006.