Piano multipitch estimation using sparse coding embedded deep learning

As the foundation of many applications, multipitch estimation problem has always been the focus of acoustic music processing; however, existing algorithms perform deficiently due to its complexity. In this paper, we employ deep learning to address piano multipitch estimation problem by proposing MPE...

Full description

Saved in:
Bibliographic Details
Published in:EURASIP journal on audio, speech, and music processing Vol. 2018; no. 1; pp. 1 - 23
Main Authors: Li, Xingda, Guan, Yujing, Wu, Yingnian, Zhang, Zhongbo
Format: Journal Article
Language:English
Published: Cham Springer International Publishing 12.09.2018
Springer Nature B.V
SpringerOpen
Subjects:
Acoustics
Algorithms
Deep foundations
Deep learning
Distance learning
Engineering
Engineering Acoustics
Mathematics in Music
Multimodal NMF
Multipitch estimation
Music
Non-negative incoherent dictionary learning
Non-negative sparse coding
Regularization
Signal,Image and Speech Processing
Deep learning
Non-negative sparse coding
Multipitch estimation
Non-negative incoherent dictionary learning
Multimodal NMF
ISSN:1687-4722, 1687-4714, 1687-4722
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:As the foundation of many applications, multipitch estimation problem has always been the focus of acoustic music processing; however, existing algorithms perform deficiently due to its complexity. In this paper, we employ deep learning to address piano multipitch estimation problem by proposing MPENet based on a novel multimodal sparse incoherent non-negative matrix factorization (NMF) layer . This layer originates from a multimodal NMF problem with Lorentzian-BlockFrobenius sparsity constraint and incoherentness regularization. Experiments show that MPENet achieves state-of-the-art performance (83.65% F-measure for polyphony level 6) on RAND subset of MAPS dataset. MPENet enables NMF to do online learning and accomplishes multi-label classification by using only monophonic samples as training data. In addition, our layer algorithms can be easily modified and redeveloped for a wide variety of problems.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1687-4722
1687-4714
1687-4722
DOI:10.1186/s13636-018-0132-x