Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/107138
Title: | Information maximized variational domain adversarial learning for speaker verification | Authors: | Tu, Y Mak, MW Chien, JT |
Issue Date: | 2020 | Source: | In Proceedings of ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 04-08 May 2020, Barcelona, Spain, p. 6449-6453 | Abstract: | 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. | Keywords: | Adversarial training Domain adaptation Mutual information Speaker verification Variational autoencoder |
Publisher: | Institute of Electrical and Electronics Engineers | ISBN: | 978-1-5090-6631-5 (Electronic) 978-1-5090-6632-2 (Print on Demand(PoD)) |
DOI: | 10.1109/ICASSP40776.2020.9053735 | Description: | ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 04-08 May 2020, Barcelona, Spain | Rights: | ©2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The following publication Y. Tu, M. -W. Mak and J. -T. Chien, "Information Maximized Variational Domain Adversarial Learning for Speaker Verification," ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2020, pp. 6449-6453 is available at https://doi.org/10.1109/ICASSP40776.2020.9053735. |
Appears in Collections: | Conference Paper |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Tu_Information_Maximized_Variational.pdf | Pre-Published version | 745.46 kB | Adobe PDF | View/Open |
Page views
1
Citations as of Jun 30, 2024
SCOPUSTM
Citations
8
Citations as of Jun 21, 2024
WEB OF SCIENCETM
Citations
6
Citations as of Jun 27, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.