Supervised Chorus Detection for Popular Music Using Convolutional Neural Network and Multi-task Learning
This work addresses a domain-specific problem in music information retrieval, offering an incremental improvement over traditional unsupervised methods for chorus detection.
The paper tackles the problem of detecting chorus segments in popular music by introducing a supervised approach using a convolutional neural network with multi-task learning, which outperforms existing unsupervised methods on three datasets.
This paper presents a novel supervised approach to detecting the chorus segments in popular music. Traditional approaches to this task are mostly unsupervised, with pipelines designed to target some quality that is assumed to define "chorusness," which usually means seeking the loudest or most frequently repeated sections. We propose to use a convolutional neural network with a multi-task learning objective, which simultaneously fits two temporal activation curves: one indicating "chorusness" as a function of time, and the other the location of the boundaries. We also propose a post-processing method that jointly takes into account the chorus and boundary predictions to produce binary output. In experiments using three datasets, we compare our system to a set of public implementations of other segmentation and chorus-detection algorithms, and find our approach performs significantly better.