Some initial works have appeared that began to deal with the complicated task of musical instrument recognition in multi-instrumental music. Although quite a few papers have already appeared on instrument recognition of singleinstrument musical phrases (solos), the work on solo recognition is not yet exhausted. The knowledge of how to deal well with solos can also help in recognition of multiinstrumental music. We present a process for recognition of a set of instruments (bassoon, clarinet, flute, guitar, piano, cello and violin) in solo recordings, which yields a high recognition rate. Among the points that distinguish our work are a large and very diverse solo database 108 different solos, all by different performers, which apparently supplies a good generalization of the sound possibilities of each instrument, and a large collection of features 62 different feature types. Using our GDE feature selection algorithm we minimize the feature set and present the 20 features which are most suitable for solo recognition in real-time, almost without compromising the high recognition rate. The paper ends by demonstrating that our real-time feature set can also help performing instrument recognition in duet music.
Contribution au colloque ou congrès : ICMC 2004