Tempo detection using a hybrid multiband approach

In this paper, a novel tempo detection system is presented, which suggests the use of a hybrid multiband decomposition. The model tracks the periodicities of different signal property changes that manifest within different frequency bands by using the most appropriate onset/transient detectors for each frequency band. In addition, the proposed system applies a novel method to weight tempo candidates. Each contribution is evaluated by comparing the presented system against existing approaches using three different databases that comprises 1638 songs. These databases include the two publicly available database of songs used in the tempo evaluation contest of ISMIR 2004. These songs are used in order to compare the proposed approach against four recent existing approaches and also against the participants of the tempo detection contest of ISMIR 2004. The results show that the presented approach provides an improvement over existing techniques.