DEAAN: Disentangled Embedding and Adversarial Adaptation Network for Robust Speaker Representation Learning

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 demonstrate that our proposed framework can effectively generate more speaker-discriminative and domain-invariant speaker representations with a relative 20.3% reduction of EER compared to the original ResNet-based system.

arXiv commentAccepted to ICASSP 2021

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• VoxCeleb2: Deep Speaker Recognition
• VoxCeleb: a large-scale speaker identification dataset
• DRIT++: Diverse Image-to-Image Translation via Disentangled Representations
• Adversarial Speaker Verification
• Cross-lingual Text-independent Speaker Verification using Unsupervised Adversarial Discriminative Domain Adaptation
• Voices Obscured in Complex Environmental Settings (VOICES) corpus