Contrastive Adversarial Domain Adaptation Networks for Speaker Recognition

Longxin Li, Man Wai Mak, Jen Tzung Chien

Research output: Journal article publicationJournal articleAcademic researchpeer-review

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.

Original languageEnglish
JournalIEEE Transactions on Neural Networks and Learning Systems
DOIs
Publication statusAccepted/In press - 2020

Keywords

  • Adaptation models
  • Adversarial learning
  • Data mining
  • Data models
  • domain adaptation
  • domain adversarial networks (DANs)
  • domain invariance
  • Feature extraction
  • Speaker recognition
  • speaker recognition.
  • Task analysis
  • Training

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this