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

facebooktwittermailshare

Separake: Source separation with a little help from echoes

Abstract: 

It is commonly believed that multipath hurts various audio processing algorithms. At odds with this belief, we show that multipath in fact helps sound source separation, even with very simple propagation models. Unlike most existing methods, we neither ignore the room impulse responses, nor we attempt to estimate them fully. We rather assume to know the positions of a few virtual microphones generated by echoes and we show how this gives us enough spatial diversity to get a performance boost over the anechoic case. We show improvements for two standard algorithms—one that uses only magnitudes of the transfer functions, and one that also uses the phases. Concretely, we show that multi-channel non-negative matrix factorization aided with a small number of echoes beats the vanilla variant of the same algorithm, and that with magnitude information only, echoes enable separation where it was previously impossible.

up
0 users have voted:

Paper Details

Authors:
Robin Scheibler, Diego Di Carlo, Antoine Deleforge, Ivan Dokmanic
Submitted On:
22 April 2018 - 9:05pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Robin Scheibler
Paper Code:
3088
Document Year:
2018
Cite

Document Files

separake_icassp2018_slides.pdf

(71 downloads)

Subscribe

[1] Robin Scheibler, Diego Di Carlo, Antoine Deleforge, Ivan Dokmanic, "Separake: Source separation with a little help from echoes", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3139. Accessed: Sep. 25, 2018.
@article{3139-18,
url = {http://sigport.org/3139},
author = {Robin Scheibler; Diego Di Carlo; Antoine Deleforge; Ivan Dokmanic },
publisher = {IEEE SigPort},
title = {Separake: Source separation with a little help from echoes},
year = {2018} }
TY - EJOUR
T1 - Separake: Source separation with a little help from echoes
AU - Robin Scheibler; Diego Di Carlo; Antoine Deleforge; Ivan Dokmanic
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3139
ER -
Robin Scheibler, Diego Di Carlo, Antoine Deleforge, Ivan Dokmanic. (2018). Separake: Source separation with a little help from echoes. IEEE SigPort. http://sigport.org/3139
Robin Scheibler, Diego Di Carlo, Antoine Deleforge, Ivan Dokmanic, 2018. Separake: Source separation with a little help from echoes. Available at: http://sigport.org/3139.
Robin Scheibler, Diego Di Carlo, Antoine Deleforge, Ivan Dokmanic. (2018). "Separake: Source separation with a little help from echoes." Web.
1. Robin Scheibler, Diego Di Carlo, Antoine Deleforge, Ivan Dokmanic. Separake: Source separation with a little help from echoes [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3139