Chorus Detection Using Music Structure Analysis

摘要

This paper describes a novel chorus detection method based on extracting the functional structure of music from its self-similarity matrix. An existing similarity measure was enhanced firstly by using a key-shift invariant distance and by introducing a chroma-like pitch feature that exploits melody extraction results of the music. The repeated sections in the audio were extracted using a graph-based algorithm and clustering-merging method assuming transitivity of similarity then. Finally, a classifier to detect the chorus from the repeated sections was trained. The evaluation results show that our method is comparable with the state-of-the-art algorithms on both multiple and single chorus section detection tasks.