Reducing Tempo Octave Errors by Periodicity Vector Coding And SVM Learning

In this paper we present a method for learning tempo classes in order to reduce tempo octave errors. There are two main contributions of this paper in the rhythm analysis field. Firstly, a novel technique is proposed to code the rhythm periodicity functions of a music signal. Target tempi range is divided into overlapping “tempo bands” and the periodicity function is filtered by triangular masks aligned to those tempo bands, in order to calculate the respective saliencies, followed by the application of the DCT transform on band strengths. The second contribution is the adoption of Support Vector Machines to learn broad tempo classes from the coded periodicity vectors. Training instances are assigned a tempo class according to annotated tempo. The classes are assumed to correspond to “music speed”. At classification phase, each target excerpt is assigned a tempo class label by the SVM. Target periodicity vector is masked by the predicted tempo class range, and tempo is estimated by peak picking in the reduced periodicity vector. The proposed method was evaluated on the benchmark ISMIR 2004 Tempo Induction Evaluation Exchange Dataset for both tempo class and tempo value estimation tasks. Results indicate that the proposed approach provides an efficient framework to tackle the tempo estimation task.