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

Adversarial/Discriminative Training and Spoofing for Speaker Recognition

A Generalized Framework for Domain Adaptation of PLDA in Speaker Recognition


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.

Paper Details

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

Document Files

Presentation material

(26)

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: Aug. 10, 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

ICASSP2020 TEXT-INDEPENDENT SPEAKER VERIFICATION WITH ADVERSARIAL LEARNING ON SHORT UTTERANCES


A text-independent speaker verification system suffers severe performance degradation under short utterance condition. To address the problem, in this paper, we propose an adversarially learned embedding mapping model that directly maps a short embedding to an enhanced embedding with increased discriminability. In particular, a Wasserstein GAN with a bunch of loss criteria are investigated. These loss functions have distinct optimization objectives and some of them are less favoured for the speaker verification research area.

Paper Details

Authors:
KAI LIU, HUAN ZHOU
Submitted On:
13 May 2020 - 9:57pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Adversarial Learning, Speaker Recognition, Short utterances

(34)

Subscribe

[1] KAI LIU, HUAN ZHOU, "ICASSP2020 TEXT-INDEPENDENT SPEAKER VERIFICATION WITH ADVERSARIAL LEARNING ON SHORT UTTERANCES", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5185. Accessed: Aug. 10, 2020.
@article{5185-20,
url = {http://sigport.org/5185},
author = {KAI LIU; HUAN ZHOU },
publisher = {IEEE SigPort},
title = {ICASSP2020 TEXT-INDEPENDENT SPEAKER VERIFICATION WITH ADVERSARIAL LEARNING ON SHORT UTTERANCES},
year = {2020} }
TY - EJOUR
T1 - ICASSP2020 TEXT-INDEPENDENT SPEAKER VERIFICATION WITH ADVERSARIAL LEARNING ON SHORT UTTERANCES
AU - KAI LIU; HUAN ZHOU
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5185
ER -
KAI LIU, HUAN ZHOU. (2020). ICASSP2020 TEXT-INDEPENDENT SPEAKER VERIFICATION WITH ADVERSARIAL LEARNING ON SHORT UTTERANCES. IEEE SigPort. http://sigport.org/5185
KAI LIU, HUAN ZHOU, 2020. ICASSP2020 TEXT-INDEPENDENT SPEAKER VERIFICATION WITH ADVERSARIAL LEARNING ON SHORT UTTERANCES. Available at: http://sigport.org/5185.
KAI LIU, HUAN ZHOU. (2020). "ICASSP2020 TEXT-INDEPENDENT SPEAKER VERIFICATION WITH ADVERSARIAL LEARNING ON SHORT UTTERANCES." Web.
1. KAI LIU, HUAN ZHOU. ICASSP2020 TEXT-INDEPENDENT SPEAKER VERIFICATION WITH ADVERSARIAL LEARNING ON SHORT UTTERANCES [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5185