Cemgil A.T. & Kappen, B. (2002) Integrating Tempo Tracking and Quantization using Particle Filtering. Proceedings of 2002 International Computer Music Conference.

Abstract

We present a probabilistic switching state space model for timing deviations in expressive music performance. We formulate tempo tracking and automatic transcription (rhythm quantization) as filtering and maximum a posteriori (MAP) state estimation tasks. The resulting model is suitable for real-time tempo tracking and transcription and hence useful in a number of music applications such as adaptive automatic accompaniment and score typesetting.

Full paper (pdf)