Variational Domain Adversarial Learning With Mutual Information Maximization for Speaker Verification
- 24 June 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 28 (23299290) , 2013-2024
Abstract
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.Keywords
Funding Information
- RGC of Hong Kong SAR (PolyU 152137/17E)
- Taiwan MOST (109-2634-F-009-024)
This publication has 30 references indexed in Scilit:
- Adversarial domain separation and adaptation2017
- Autoencoder Based Domain Adaptation for Speaker Recognition Under Insufficient Channel Information2017
- Generating Sentences from a Continuous Space2016
- Improving speaker recognition performance in the domain adaptation challenge using deep neural networks2014
- Inter dataset variability compensation for speaker recognition2014
- Front-End Factor Analysis for Speaker VerificationIEEE Transactions on Audio, Speech, and Language Processing, 2010
- Probabilistic Linear Discriminant Analysis for Inferences About Identity2007
- Some statistical issues in the comparison of speech recognition algorithms2003
- Probability Plotting Methods for the Analysis of DataBiometrika, 1968
- An Analysis of Variance Test for Normality (Complete Samples)Biometrika, 1965