| Paper ID | AUD-21.1 |
| Paper Title |
Supervised Chorus Detection for Popular Music Using Convolutional Neural Network and Multi-task Learning |
| Authors |
Ju-Chiang Wang, Jordan B. L. Smith, Jitong Chen, Xuchen Song, Yuxuan Wang, ByteDance, United States |
| Session | AUD-21: Music Information Retrieval and Music Language Processing 4: Structure and Alignment |
| Location | Gather.Town |
| Session Time: | Thursday, 10 June, 14:00 - 14:45 |
| Presentation Time: | Thursday, 10 June, 14:00 - 14:45 |
| Presentation |
Poster
|
| Topic |
Audio and Acoustic Signal Processing: [AUD-MIR] Music Information Retrieval and Music Language Processing |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
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. |
