Browsing by Author "Tu, Youzhi"

Now showing 1 - 2 of 2

SEMI-SUPERVISED NUISANCE-ATTRIBUTE NETWORKS FOR DOMAIN ADAPTATION
(2019-01-01)
Lin, Weiwei
;
Mak, Man-Wai
;
Tu, Youzhi
;
Chien, Jen-Tzung
;
電機工程學系
How to overcome the training and test data mismatch in speaker verification systems has been a focus of research recently. In this paper, we propose a semi-supervised nuisance attribute network ( SNAN) to reduce the domain mismatch in i-vectors and x-vectors. SNANs are based on the idea of nuisance attribute removal in inter-dataset variability compensation ( IDVC). But instead of measuring the domain variability through the dataset means, SNANs use the maximum mean discrepancy ( MMD) as part of their loss function, which enables the network to find nuisance directions in which domain variability is measured up to infinite moment. The architecture of SNANs also allows us to incorporate the out-of-domain speaker labels into the semi-supervised training process through the center loss and triplet loss. Using SNANs as a preprocessing step for PLDA training, we achieve a relative improvement of 11.8% in EER on NIST 2016 SRE compared to PLDA without adaptation. We also found that the semi-supervised approach can further improve SNANs' performance.
Variational Domain Adversarial Learning With Mutual Information Maximization for Speaker Verification
(2020-01-01)
Tu, Youzhi
;
Mak, Man-Wai
;
Chien, Jen-Tzung
;
電機工程學系
;
Department of Electrical and Computer Engineering
Domain mismatch is a common problem in speaker verification (SV) and often causes performance degradation. For the system relying on the Gaussian PLDA backend to suppress the channel variability, the performance would be further limited if there is no Gaussianity constraint on the learned embeddings. This paper proposes an information-maximized variational domain adversarial neural network (InfoVDANN) that incorporates an InfoVAE into domain adversarial training (DAT) to reduce domain mismatch and simultaneously meet the Gaussianity requirement of the PLDA backend. Specifically, DAT is applied to produce speaker discriminative and domain-invariant features, while the InfoVAE performs variational regularization on the embedded features so that they follow a Gaussian distribution. Another benefit of the InfoVAE is that it avoids posterior collapse in VAEs by preserving the mutual information between the embedded features and the training set so that extra speaker information can be retained in the features. Experiments on both SRE16 and SRE18-CMN2 show that the InfoVDANN outperforms the recent VDANN, which suggests that increasing the mutual information between the embedded features and input features enables the InfoVDANN to extract extra speaker information that is otherwise not possible.