IMPROVING INSTRUMENT RECOGNITION IN POLYPHONIC MUSIC THROUGH SYSTEM INTEGRATION

A method is proposed for instrument recognition in polyphonic mu-sic which combines two independent detector systems. A poly-phonic musical instrument recognition system using a missing fea-ture approach and an automatic music transcription system based on shift invariant probabilistic latent component analysis that includes instrument assignment. We propose a method to integrate the two systems by fusing the instrument contributions estimated by the first system onto the transcription system in the form of Dirichlet priors. Both systems, as well as the integrated system are evaluated using a dataset of continuous polyphonic music recordings. Detailed re-sults that highlight a clear improvement in the performance of the integrated system are reported for different training conditions. Index Terms — Musical instrument recognition, automatic mu-sic transcription, music signal analysis 1