Interactive musical systems require real-time, low-latency, accurate, and reliable event detection and classification algorithms. In this paper, we introduce a model-based algorithm for detection of percussive events and test the algorithm on the detection and classification of different percussive sounds. We focus on tuning the algorithm for a good compromise between temporal precision, classification accuracy and low latency. The model is trained offline on different percussive sounds using the expectation maximization approach for learning spectral templates for each sound and is able to run online to detect and classify sounds from audio stream input by a Hidden Markov Model. Our results indicate that the approach is promising and applicable in design and development of interactive musical systems.