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

facebooktwittermailshare

A Generalized Framework for Domain Adaptation of PLDA in Speaker Recognition

Abstract: 

This paper proposes a generalized framework for domain adaptation of Probabilistic Linear Discriminant Analysis (PLDA) in speaker recognition. It not only includes several existing supervised and unsupervised domain adaptation methods but also makes possible more flexible usage of available data in different domains. In particular, we introduce here the two new techniques described below. (1) Correlation-alignment-based interpolation and (2) covariance regularization. The proposed correlation-alignment-based interpolation method decreases minCprimary up to 30.5% as compared with that from an out-of-domain PLDA model
before adaptation, and minCprimary is also 5.5% lower than with a conventional linear interpolation method with optimal interpolation weights. Further, the proposed regularization technique ensures robustness in interpolations w.r.t. varying
interpolation weights, which in practice is essential.

up
0 users have voted:

Paper Details

Authors:
Qiongqiong Wang, Koji Okabe, Kong Aik Lee, Takafumi Koshinaka
Submitted On:
20 May 2020 - 8:49pm
Short Link:
Type:
Presentation Slides
Event:
Document Year:
2020
Cite

Document Files

Presentation material

(7)

Subscribe

[1] Qiongqiong Wang, Koji Okabe, Kong Aik Lee, Takafumi Koshinaka, "A Generalized Framework for Domain Adaptation of PLDA in Speaker Recognition", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5422. Accessed: Jun. 06, 2020.
@article{5422-20,
url = {http://sigport.org/5422},
author = {Qiongqiong Wang; Koji Okabe; Kong Aik Lee; Takafumi Koshinaka },
publisher = {IEEE SigPort},
title = {A Generalized Framework for Domain Adaptation of PLDA in Speaker Recognition},
year = {2020} }
TY - EJOUR
T1 - A Generalized Framework for Domain Adaptation of PLDA in Speaker Recognition
AU - Qiongqiong Wang; Koji Okabe; Kong Aik Lee; Takafumi Koshinaka
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5422
ER -
Qiongqiong Wang, Koji Okabe, Kong Aik Lee, Takafumi Koshinaka. (2020). A Generalized Framework for Domain Adaptation of PLDA in Speaker Recognition. IEEE SigPort. http://sigport.org/5422
Qiongqiong Wang, Koji Okabe, Kong Aik Lee, Takafumi Koshinaka, 2020. A Generalized Framework for Domain Adaptation of PLDA in Speaker Recognition. Available at: http://sigport.org/5422.
Qiongqiong Wang, Koji Okabe, Kong Aik Lee, Takafumi Koshinaka. (2020). "A Generalized Framework for Domain Adaptation of PLDA in Speaker Recognition." Web.
1. Qiongqiong Wang, Koji Okabe, Kong Aik Lee, Takafumi Koshinaka. A Generalized Framework for Domain Adaptation of PLDA in Speaker Recognition [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5422