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

facebooktwittermailshare

Multiple-input neural network-based residual echo suppression

Abstract: 

A residual echo suppressor (RES) aims to suppress the residual echo in the output of an acoustic echo canceler (AEC). Spectral-based RES approaches typically estimate the magnitude spectra of the near-end speech and the residual echo from a single input, that is either the far-end speech or the echo computed by the AEC, and derive the RES filter coefficients accordingly. These single inputs do not always suffice to discriminate the near-end speech from the remaining echo. In this paper, we propose a neural network-based approach that directly estimates the RES filter coefficients from multiple inputs, including the AEC output, the far-end speech, and/or the echo computed by the AEC. We evaluate our system on real recordings of acoustic echo and near-end speech acquired in various situations with a smart speaker. We compare it to two single-input spectral-based approaches in terms of echo reduction and near-end speech distortion.

up
0 users have voted:

Paper Details

Authors:
Guillaume Carbajal, Romain Serizel, Emmanuel Vincent, Eric Humbert
Submitted On:
25 April 2018 - 5:13am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Guillaume CARBAJAL
Paper Code:
AASP-P1.5
Document Year:
2018
Cite

Document Files

posterICASSP_CARBAJAL.pdf

(101 downloads)

Subscribe

[1] Guillaume Carbajal, Romain Serizel, Emmanuel Vincent, Eric Humbert, "Multiple-input neural network-based residual echo suppression", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3178. Accessed: Dec. 18, 2018.
@article{3178-18,
url = {http://sigport.org/3178},
author = {Guillaume Carbajal; Romain Serizel; Emmanuel Vincent; Eric Humbert },
publisher = {IEEE SigPort},
title = {Multiple-input neural network-based residual echo suppression},
year = {2018} }
TY - EJOUR
T1 - Multiple-input neural network-based residual echo suppression
AU - Guillaume Carbajal; Romain Serizel; Emmanuel Vincent; Eric Humbert
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3178
ER -
Guillaume Carbajal, Romain Serizel, Emmanuel Vincent, Eric Humbert. (2018). Multiple-input neural network-based residual echo suppression. IEEE SigPort. http://sigport.org/3178
Guillaume Carbajal, Romain Serizel, Emmanuel Vincent, Eric Humbert, 2018. Multiple-input neural network-based residual echo suppression. Available at: http://sigport.org/3178.
Guillaume Carbajal, Romain Serizel, Emmanuel Vincent, Eric Humbert. (2018). "Multiple-input neural network-based residual echo suppression." Web.
1. Guillaume Carbajal, Romain Serizel, Emmanuel Vincent, Eric Humbert. Multiple-input neural network-based residual echo suppression [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3178