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

facebooktwittermailshare

Robust speaker recognition using unsupervised adversarial invariance

Abstract: 

In this paper, we address the problem of speaker recognition in challenging acoustic conditions using a novel method to extract robust speaker-discriminative speech representations. We adopt a recently proposed unsupervised adversarial invariance architecture to train a network that maps speaker embeddings extracted using a pre-trained model onto two lower dimensional embedding spaces. The embedding spaces are learnt to disentangle speaker-discriminative information from all other information present in the audio recordings, without supervision about the acoustic conditions. We analyze the robustness of the proposed embeddings to various sources of variability present in the signal for speaker verification and unsupervised clustering tasks on a large-scale speaker recognition corpus. Our analyses show that the proposed system substantially outperforms the baseline in a variety of challenging acoustic scenarios. Furthermore, for the task of speaker diarization on a real-world meeting corpus, our system shows a relative improvement of 36% in the diarization error rate compared to the state-of-the-art baseline.

up
0 users have voted:

Paper Details

Authors:
Monisankha Pal, Shrikanth Narayanan
Submitted On:
5 May 2020 - 1:34am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Raghuveer Peri
Paper Code:
5301
Document Year:
2020
Cite

Document Files

Raghuveer_Peri_ICASSP2020.pdf

(19)

Subscribe

[1] Monisankha Pal, Shrikanth Narayanan, "Robust speaker recognition using unsupervised adversarial invariance", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5123. Accessed: Jul. 04, 2020.
@article{5123-20,
url = {http://sigport.org/5123},
author = {Monisankha Pal; Shrikanth Narayanan },
publisher = {IEEE SigPort},
title = {Robust speaker recognition using unsupervised adversarial invariance},
year = {2020} }
TY - EJOUR
T1 - Robust speaker recognition using unsupervised adversarial invariance
AU - Monisankha Pal; Shrikanth Narayanan
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5123
ER -
Monisankha Pal, Shrikanth Narayanan. (2020). Robust speaker recognition using unsupervised adversarial invariance. IEEE SigPort. http://sigport.org/5123
Monisankha Pal, Shrikanth Narayanan, 2020. Robust speaker recognition using unsupervised adversarial invariance. Available at: http://sigport.org/5123.
Monisankha Pal, Shrikanth Narayanan. (2020). "Robust speaker recognition using unsupervised adversarial invariance." Web.
1. Monisankha Pal, Shrikanth Narayanan. Robust speaker recognition using unsupervised adversarial invariance [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5123