A Music Structure Informed Downbeat Tracking System Using Skip-chain Conditional Random Fields and Deep Learning

In recent years the task of downbeat tracking has received increasing attention and the state of the art has been improved with the introduction of deep learning methods. Among proposed solutions, existing systems exploit short-term musical rules as part of their language modelling. In this work we...

Full description

Saved in:
Bibliographic Details
Main Authors: Fuentes, Magdalena, McFee, Brian, Crayencour, Helene C., Essid, Slim, Bello, Juan Pablo
Format: Conference Proceeding
Language:English
Subjects:
Bars
Convolutional-Recurrent Neural Networks
Deep learning
Downbeat Tracking
Estimation
Hidden Markov models
Music
Music Structure
Skip-Chain Conditional Random Fields
Task analysis
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In recent years the task of downbeat tracking has received increasing attention and the state of the art has been improved with the introduction of deep learning methods. Among proposed solutions, existing systems exploit short-term musical rules as part of their language modelling. In this work we show in an oracle scenario how including longer-term musical rules, in particular music structure, can enhance downbeat estimation. We introduce a skip-chain conditional random field language model for downbeat tracking designed to include section information in an unified and flexible framework. We combine this model with a state-of-the-art convolutional-recurrent network and we contrast the system's performance to the commonly used Bar Pointer model. Our experiments on the popular Beatles dataset show that incorporating structure information in the language model leads to more consistent and more robust downbeat estimations.
ISSN:2379-190X
DOI:10.1109/ICASSP.2019.8682870