Multitask Learning for Fundamental Frequency Estimation in Music
Sound
2018-09-05 v1 Machine Learning
Audio and Speech Processing
Machine Learning
Abstract
Fundamental frequency (f0) estimation from polyphonic music includes the tasks of multiple-f0, melody, vocal, and bass line estimation. Historically these problems have been approached separately, and only recently, using learning-based approaches. We present a multitask deep learning architecture that jointly estimates outputs for various tasks including multiple-f0, melody, vocal and bass line estimation, and is trained using a large, semi-automatically annotated dataset. We show that the multitask model outperforms its single-task counterparts, and explore the effect of various design decisions in our approach, and show that it performs better or at least competitively when compared against strong baseline methods.
Cite
@article{arxiv.1809.00381,
title = {Multitask Learning for Fundamental Frequency Estimation in Music},
author = {Rachel M. Bittner and Brian McFee and Juan P. Bello},
journal= {arXiv preprint arXiv:1809.00381},
year = {2018}
}