Logo image
Back
HARMONIC VARIABLE-SIZE DICTIONARY LEARNING FOR MUSIC SOURCE SEPARATION
Conference proceeding

HARMONIC VARIABLE-SIZE DICTIONARY LEARNING FOR MUSIC SOURCE SEPARATION

Steven K. Tjoa, Matthew C. Stamm, W. Sabrina Lin, K. J. Ray Liu and IEEE
2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, pp 413-416
01 Jan 2010
DOI: https://doi.org/10.1109/ICASSP.2010.5495773

Abstract

Acoustics Computer Science Computer Science, Theory & Methods Engineering Engineering, Electrical & Electronic Science & Technology Technology
Dictionary learning through matrix factorization has become widely popular for performing music transcription and source separation. These methods learn a concise set of dictionary atoms which represent spectrograms of musical objects. However, there is no guarantee that the atoms learned will be perceptually meaningful, particularly when there exists significant spectral and temporal overlap among the musical sources. In this paper, we propose a novel dictionary learning method that imposes additional harmonic constraints upon the atoms of the learned dictionary while allowing the dictionary size to grow appropriately during the learning procedure. When there is significant spectral-temporal overlap among the musical sources, our method outperforms popular existing matrix factorization methods as measured by the recall and precision of learned dictionary atoms.

Metrics

8 Record Views
4 citations in Web of Science
6 citations in Scopus

Details

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Web of Science research areas
Acoustics
Computer Science, Theory & Methods
Engineering, Electrical & Electronic
Logo image