Hierarchical parametrisation and classification for musical instrument recognition

The extraction of the timbre for musical identification from the audio signal has been subject of several researches, where various spectro-temporal parameters have been proposed and compared. Classification strategies are generally based on two discrimination approaches: direct classification and hierarchical classification. In both strategies, the feature vector is static and is used during the whole treatment process. In this paper, we propose a hierarchical classification where the feature vector is dynamic and changes depending on each level and each node of the hierarchical tree. The feature vector is optimized and is determined with the sequential backward selection (SBS) algorithm. Using a large database (RWC), the results show a score gain in musical instrument recognition performances with the proposed approach compared to reference systems.