Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/107147
Title: | Contrastive adversarial domain adaptation networks for speaker recognition | Authors: | Li, L Mak, MW Chien, JT |
Issue Date: | May-2022 | Source: | IEEE transactions on neural networks and learning systems, May 2022, v. 33, no. 5, p. 2236-2245 | Abstract: | Domain adaptation aims to reduce the mismatch between the source and target domains. A domain adversarial network (DAN) has been recently proposed to incorporate adversarial learning into deep neural networks to create a domain-invariant space. However, DAN's major drawback is that it is difficult to find the domain-invariant space by using a single feature extractor. In this article, we propose to split the feature extractor into two contrastive branches, with one branch delegating for the class-dependence in the latent space and another branch focusing on domain-invariance. The feature extractor achieves these contrastive goals by sharing the first and last hidden layers but possessing decoupled branches in the middle hidden layers. For encouraging the feature extractor to produce class-discriminative embedded features, the label predictor is adversarially trained to produce equal posterior probabilities across all of the outputs instead of producing one-hot outputs. We refer to the resulting domain adaptation network as 'contrastive adversarial domain adaptation network (CADAN).' We evaluated the embedded features' domain-invariance via a series of speaker identification experiments under both clean and noisy conditions. Results demonstrate that the embedded features produced by CADAN lead to a 33% improvement in speaker identification accuracy compared with the conventional DAN. | Keywords: | Adversarial learning Domain adaptation Domain adversarial networks (DANs) Domain invariance Speaker recognition |
Publisher: | Institute of Electrical and Electronics Engineers | Journal: | IEEE transactions on neural networks and learning systems | ISSN: | 2162-237X | EISSN: | 2162-2388 | DOI: | 10.1109/TNNLS.2020.3044215 | 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 L. Li, M. -W. Mak and J. -T. Chien, "Contrastive Adversarial Domain Adaptation Networks for Speaker Recognition," in IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 5, pp. 2236-2245, May 2022 is available at https://doi.org/10.1109/TNNLS.2020.3044215. |
Appears in Collections: | Journal/Magazine Article |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Li_Contrastive_Adversarial_Domain.pdf | Pre-Published version | 1.01 MB | Adobe PDF | View/Open |
Page views
2
Citations as of Jun 30, 2024
Downloads
2
Citations as of Jun 30, 2024
SCOPUSTM
Citations
15
Citations as of Jun 27, 2024
WEB OF SCIENCETM
Citations
11
Citations as of Jun 27, 2024
![](/image/google_scholar.jpg)
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.