Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Shift-Invariant Kernel Additive Modelling for Audio Source Separation

Abstract: 

A major goal in blind source separation to identify and separate sources is to model their inherent characteristics. While most state-of- the-art approaches are supervised methods trained on large datasets, interest in non-data-driven approaches such as Kernel Additive Modelling (KAM) remains high due to their interpretability and adaptability. KAM performs the separation of a given source applying robust statistics on the time-frequency bins selected by a source-specific kernel function, commonly the K-NN function. This choice assumes that the source of interest repeats in both time and frequency. In practice, this assumption does not always hold. Therefore, we introduce a shift-invariant kernel function capable of identifying similar spectral content even under frequency shifts. This way, we can considerably increase the amount of suitable sound material available to the robust statistics. While this leads to an increase in separation performance, a basic formulation, however, is computationally expensive. Therefore, we additionally present acceleration techniques that lower the overall computational complexity.

up
0 users have voted:

Comments

Image upload

Paper Details

Authors:
D. Fano Yela, S. Ewert, K. O'Hanlon, M. Sandler
Submitted On:
21 April 2018 - 10:11pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Delia Fano Yela
Paper Code:
AASP-P9.7
Document Year:
2018
Cite

Document Files

dfy_poster.pdf

(29 downloads)

Subscribe

[1] D. Fano Yela, S. Ewert, K. O'Hanlon, M. Sandler, "Shift-Invariant Kernel Additive Modelling for Audio Source Separation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3125. Accessed: Jun. 22, 2018.
@article{3125-18,
url = {http://sigport.org/3125},
author = {D. Fano Yela; S. Ewert; K. O'Hanlon; M. Sandler },
publisher = {IEEE SigPort},
title = {Shift-Invariant Kernel Additive Modelling for Audio Source Separation},
year = {2018} }
TY - EJOUR
T1 - Shift-Invariant Kernel Additive Modelling for Audio Source Separation
AU - D. Fano Yela; S. Ewert; K. O'Hanlon; M. Sandler
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3125
ER -
D. Fano Yela, S. Ewert, K. O'Hanlon, M. Sandler. (2018). Shift-Invariant Kernel Additive Modelling for Audio Source Separation. IEEE SigPort. http://sigport.org/3125
D. Fano Yela, S. Ewert, K. O'Hanlon, M. Sandler, 2018. Shift-Invariant Kernel Additive Modelling for Audio Source Separation. Available at: http://sigport.org/3125.
D. Fano Yela, S. Ewert, K. O'Hanlon, M. Sandler. (2018). "Shift-Invariant Kernel Additive Modelling for Audio Source Separation." Web.
1. D. Fano Yela, S. Ewert, K. O'Hanlon, M. Sandler. Shift-Invariant Kernel Additive Modelling for Audio Source Separation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3125