• Home
  • Search
  • Multi-Source Domain Adaptation and Fusion for Speaker Verification
  • Cite Icon8
  • https://doi.org/10.1109/taslp.2022.3182271Copy DOI Icon

Multi-Source Domain Adaptation and Fusion for Speaker Verification

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Recently, domain adaptation model was studied for Speaker Verification (SV) task to solve the performance reduction resulted from various mismatch between the training dataset and the testing dataset. However, since most schemes apply adaptation from single source domain to the target domain, they may not be robust enough against various mismatch between the samples in the source domain and those in the target domain. In this paper, multiple source domain adaptation and fusion model was studied to solve this problem. First, the x-vector based SV scheme is pretrained on each source domain. Second, UnShared Network (USN) combining weight regularization loss based adaptation model is adopted to adapt each pretrained model to the target domain and maintain the speaker-related feature as much as possible. Third, the Registered-Utterance-To-Test-Utterance (RUTTU) similarity matrix is constructed based on the x-vector feature extracted by the adapted model from each source domain. Fourth, the Similarity Network Fusion (SNF) technique is introduced and modified to obtain Modified Similarity Network Fusion (MSNF) scheme, which is used to fuse the RUTTU similarity matrices obtained from multiple adapted models. Finally, speaker matching is achieved by averaging the obtained fused similarities between the test utterance and each of the registered utterances of a specific speaker. Extensive experimental results demonstrate that i) the proposed fusion model outperforms the Multi-source Distilling Domain Adaptation (MDDA) model and Logistic Regression Fusion (LRF) model in SV task; ii) the USN combining weight regularization loss based adaptation strategy, the MSNF fusion scheme, and the modified speaker matching mechanism all contribute to the performance enhancement; iii) the fusion effectiveness is little influenced by the hyper-parameters setting of MSNF.

Similar Papers
  • Research Article
  • Citations1

Multi-Source Reinforced Selective Domain Adaptation for Cross-Subject and Cross-Session EEG-Based Emotion Recognition

  • Jan 01, 2025
  • IEEE Access
  • Xin Deng +4
  • Research Article

DW-D3A: dynamic weighted dual-driven domain adaptation for cross-scene hyperspectral image classification

  • Jul 01, 2024
  • International Journal of Remote Sensing
  • Ao Li +4
  • Research Article
  • Citations99

A Stacked Auto-Encoder Based Partial Adversarial Domain Adaptation Model for Intelligent Fault Diagnosis of Rotating Machines

  • Dec 15, 2020
  • IEEE Transactions on Industrial Informatics
  • Zhao-Hua Liu +5
  • Research Article
  • Citations1

Double-weighted multi-source domain adaptation model for tunnel boring machine main bearing fault diagnosis at low rotating speeds

  • May 19, 2025
  • Engineering Research Express
  • Shuaikun Zhang +5
  • Research Article
  • Citations35

Unsupervised domain adaptation with self-attention for post-disaster building damage detection

  • Jul 14, 2020
  • Neurocomputing
  • Yundong Li +5
  • Research Article
  • Citations3

Robust Deep Softmax Regression Against Label Noise for Unsupervised Domain Adaptation

  • Jun 07, 2019
  • International Journal of Pattern Recognition and Artificial Intelligence
  • Guangbin Wu +4
  • Research Article
  • Citations30

Stacked maximum independence autoencoders: A domain generalization approach for fault diagnosis under various working conditions

  • Dec 22, 2023
  • Mechanical Systems and Signal Processing
  • Shan Pang
  • Research Article
  • Citations11

Uma Contribuição para a Adaptabilidade de Ambientes Virtuais de Aprendizagem para Dispositivos Móveis

  • May 01, 2009
  • Revista Brasileira de Informática na Educação
  • Viviane De F Bartholo +2
  • Dissertation

Towards robust sensing and recognition : from statistical learning to transfer learning

  • Jan 01, 2020
  • Jianfei Yang
  • Conference Article
  • Citations9

Universal Domain Adaptation without Source Data for Remote Sensing Image Scene Classification

  • Jul 17, 2022
  • Qingsong Xu +2
  • Research Article
  • Citations45

Universal multi-Source domain adaptation for image classification

  • Aug 14, 2021
  • Pattern Recognition
  • Yueming Yin +3
  • Conference Article
  • Citations2

Co-Unet-GAN: a co-learning domain adaptation model on echocardiography segmentation

  • Apr 03, 2023
  • Junyang Cai +2
  • Conference Article
  • Citations83

Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation

  • Jun 01, 2021
  • Jianzhong He +3
  • Research Article

EDTM: Efficient Domain Transition for Multi-Source Domain Adaptation

  • Jan 01, 2026
  • Computer Modeling in Engineering & Sciences
  • Mangyu Lee +4
  • Research Article
  • Citations2

MiDA: Membership inference attacks against domain adaptation

  • Jan 20, 2023
  • ISA Transactions
  • Yuanjie Zhang +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.