DEAAN: Disentangled Embedding And Adversarial Adaptation Network For Robust Speaker Representation Learning
2020 · Mufan Sang, Wei Xia, John H. L. Hansen
Abstract
Despite speaker verification has achieved significant performance improvement with the development of deep neural networks, domain mismatch is still a challenging problem in this field. In this study, we propose a novel framework to disentangle speaker-related and domain-specific features and apply domain adaptation on the speaker-related feature space solely. Instead of performing domain adaptation directly on the feature space where domain information is not removed, using disentanglement can efficiently boost adaptation performance. To be specific, our model's input speech from the source and target domains is first encoded into different latent feature spaces. The adversarial domain adaptation is conducted on the shared speaker-related feature space to encourage the property of domain-invariance. Further, we minimize the mutual information between speaker-related and domain-specific features for both domains to enforce the disentanglement. Experimental results on the VOiCES dataset
Authors
(none)
Tags
Stats
Related papers
- Vae-based Domain Adaptation For Speaker Verification (2019)7.50
- Speaker Verification Using End-to-end Adversarial Language Adaptation (2018)11.19
- Adapting End-to-end Neural Speaker Verification To New Languages And Recording Conditions With Adversarial Training (2018)9.59
- Disentangled Representation Learning For Environment-agnostic Speaker Recognition (2024)4.82
- A Joint Noise Disentanglement And Adversarial Training Framework For Robust Speaker Verification (2024)6.34
- Disentangled Speaker And Nuisance Attribute Embedding For Robust Speaker Verification (2020)8.60
- Editnet: A Lightweight Network For Unsupervised Domain Adaptation In Speaker Verification (2022)5.84
- SEEF-ALDR: A Speaker Embedding Enhancement Framework Via Adversarial Learning Based Disentangled Representation (2019)3.58