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

facebooktwittermailshare

A DENOISING AUTOENCODER FOR SPEAKER RECOGNITION. RESULTS ON THE MCE 2018 CHALLENGE

Abstract: 

We propose a Denoising Autoencoder (DAE) for speaker recognition, trained to map each individual ivector to the mean of all ivectors belonging to that particular speaker. The aim of this DAE is to compensate for inter-session variability and increase the discriminative power of the ivectors prior to PLDA scoring. We test the proposed approach on the MCE 2018 1st Multi-target speaker detection and identification Challenge Evaluation. This evaluation presents a call-center fraud detection scenario: given a speech segment, detect if it belongs to any of the speakers in a blacklist. We show that our DAE system consistently outperforms the usual LDA + PLDA pipeline, achieving a Top-S EER of 4.33% and Top-1 EER of 6.11% on the evaluation set, which represents a 45.6% error reduction with respect to the baseline system provided by organizers.

up
0 users have voted:

Paper Details

Authors:
Roberto Font
Submitted On:
9 May 2019 - 5:56am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Roberto Font
Paper Code:
1809
Document Year:
2019
Cite

Document Files

ICASSP-2019_RobertoFont.pdf

(49)

Subscribe

[1] Roberto Font, "A DENOISING AUTOENCODER FOR SPEAKER RECOGNITION. RESULTS ON THE MCE 2018 CHALLENGE", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4180. Accessed: Nov. 11, 2019.
@article{4180-19,
url = {http://sigport.org/4180},
author = {Roberto Font },
publisher = {IEEE SigPort},
title = {A DENOISING AUTOENCODER FOR SPEAKER RECOGNITION. RESULTS ON THE MCE 2018 CHALLENGE},
year = {2019} }
TY - EJOUR
T1 - A DENOISING AUTOENCODER FOR SPEAKER RECOGNITION. RESULTS ON THE MCE 2018 CHALLENGE
AU - Roberto Font
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4180
ER -
Roberto Font. (2019). A DENOISING AUTOENCODER FOR SPEAKER RECOGNITION. RESULTS ON THE MCE 2018 CHALLENGE. IEEE SigPort. http://sigport.org/4180
Roberto Font, 2019. A DENOISING AUTOENCODER FOR SPEAKER RECOGNITION. RESULTS ON THE MCE 2018 CHALLENGE. Available at: http://sigport.org/4180.
Roberto Font. (2019). "A DENOISING AUTOENCODER FOR SPEAKER RECOGNITION. RESULTS ON THE MCE 2018 CHALLENGE." Web.
1. Roberto Font. A DENOISING AUTOENCODER FOR SPEAKER RECOGNITION. RESULTS ON THE MCE 2018 CHALLENGE [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4180