Information Maximized Variational Domain Adversarial Learning for Speaker Verification

Youzhi Tu, Man Wai Mak, Jen Tzung Chien

研究成果: Conference contribution同行評審

4 引文 斯高帕斯(Scopus)

摘要

Domain mismatch is a common problem in speaker verification. This paper proposes an information-maximized variational domain adversarial neural network (InfoVDANN) to reduce domain mismatch by incorporating an InfoVAE into domain adversarial training (DAT). DAT aims to produce speaker discriminative and domain-invariant features. The InfoVAE has two roles. First, it performs variational regularization on the learned features so that they follow a Gaussian distribution, which is essential for the standard PLDA backend. Second, it preserves mutual information between the features and the training set to extract extra speaker discriminative information. Experiments on both SRE16 and SRE18-CMN2 show that the InfoVDANN outperforms the recent VDANN, which suggests that increasing the mutual information between the latent features and input features enables the InfoVDANN to extract extra speaker information that is otherwise not possible.

原文English
主出版物標題2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
頁面6449-6453
頁數5
ISBN(電子)9781509066315
DOIs
出版狀態Published - 五月 2020
事件2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Barcelona, Spain
持續時間: 4 五月 20208 五月 2020

出版系列

名字ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
2020-May
ISSN(列印)1520-6149

Conference

Conference2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020
國家Spain
城市Barcelona
期間4/05/208/05/20

指紋 深入研究「Information Maximized Variational Domain Adversarial Learning for Speaker Verification」主題。共同形成了獨特的指紋。

引用此