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

arXiv: https://arxiv.org/abs/2012.06896 · HTML: https://mlsanity.com/paper/2012.06896/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2020.

## Built on by (most cited first, 9 of 9)

- [Self-Supervised Speaker Verification with Simple Siamese Network and Self-Supervised Regularization](https://mlsanity.com/paper/2112.04459/) (2021)
- [Learning Disentangled Behaviour Patterns for Wearable-based Human Activity Recognition](https://mlsanity.com/paper/2202.07260/) (2022)
- [Phoneme Hallucinator: One-shot Voice Conversion via Set Expansion](https://mlsanity.com/paper/2308.06382/) (2023)
- [Self-Supervised Adversarial Example Detection by Disentangled Representation](https://mlsanity.com/paper/2105.03689/) (2021)
- [Multi-Frequency Information Enhanced Channel Attention Module for Speaker Representation Learning](https://mlsanity.com/paper/2207.04540/) (2022)
- [Improving Transformer-based Networks With Locality For Automatic Speaker Verification](https://mlsanity.com/paper/2302.08639/) (2023)
- [Toward Improving Synthetic Audio Spoofing Detection Robustness via Meta-Learning and Disentangled Training With Adversarial Examples](https://mlsanity.com/paper/2408.13341/) (2024)
- [UniPET-SPK: A Unified Framework for Parameter-Efficient Tuning of Pre-trained Speech Models for Robust Speaker Verification](https://mlsanity.com/paper/2501.16542/) (2025)
- [Leveraging Speaker Embeddings with Adversarial Multi-task Learning for Age Group Classification](https://mlsanity.com/paper/2301.09058/) (2023)

## Abstract (arXiv)

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.