This talk will cover machine listening techniques for the automated real-time analysis of live drum performances. Onset detection, drum detection, beat tracking, and drum pattern analysis are combined into a system that provides rhythmic information useful in performance analysis, synchronization, and retrieval. The talk will focus on the drum detection and pattern analysis components of the the system.
For drum detection, a gamma mixture model is used to compute multiple spectral templates per drum onto which onset events can be decomposed using a technique based on non-negative matrix factorization. Unlike classification-based approaches to drum detection, this approach provides amplitude information which is invaluable in the analysis of rhythm.
The drum pattern analysis component uses a generatively pre-trained deep neural network in order to estimate high-level rhythmic information. The network is tested with beat alignment tasks, including downbeat detection, and significantly reduces alignment errors compared with a commonly used pattern correlation method.