Generalized domain adaptation framework for parametric back-end in speaker recognition
State-of-the-art speaker recognition systems comprise a speaker embedding front-end
followed by a probabilistic linear discriminant analysis (PLDA) back-end. The effectiveness …
followed by a probabilistic linear discriminant analysis (PLDA) back-end. The effectiveness …
Language agnostic speaker embedding for cross-lingual personalized speech generation
Cross-lingual personalized speech generation seeks to synthesize a target speaker's voice
from only a few training samples that are in a different language. One popular technique is to …
from only a few training samples that are in a different language. One popular technique is to …
Disentangled speaker representation learning via mutual information minimization
Domain mismatch problem caused by speaker-unrelated feature has been a major topic in
speaker recognition. In this paper, we propose an explicit disentanglement framework to …
speaker recognition. In this paper, we propose an explicit disentanglement framework to …
Multi-source domain adaptation and fusion for speaker verification
D Zhu, N Chen - IEEE/ACM Transactions on Audio, Speech …, 2022 - ieeexplore.ieee.org
Since most of the conventional domain adaptation models for Speaker Verification (SV) task
apply adaptation from single source domain to the target domain, they may not be robust …
apply adaptation from single source domain to the target domain, they may not be robust …
An Investigation of Distribution Alignment in Multi-Genre Speaker Recognition
Multi-genre speaker recognition is becoming increasingly popular due to its ability to better
represent the complexities of real-world applications. However, a major challenge is the …
represent the complexities of real-world applications. However, a major challenge is the …
CentriForce: Multiple-domain adaptation for domain-invariant speaker representation learning
Y Wei, J Du, H Liu, Z Zhang - IEEE Signal Processing Letters, 2022 - ieeexplore.ieee.org
In the real world, speaker recognition systems usually suffer from serious performance
degradation due to the domain mismatch between training and test conditions. To alleviate …
degradation due to the domain mismatch between training and test conditions. To alleviate …
Multi-Domain Adaptation by Self-Supervised Learning for Speaker Verification
W Lin, L Li, D Wang - arXiv preprint arXiv:2309.14149, 2023 - arxiv.org
In real-world applications, speaker recognition models often face various domain-mismatch
challenges, leading to a significant drop in performance. Although numerous domain …
challenges, leading to a significant drop in performance. Although numerous domain …
Adversarial data augmentation for robust speaker verification
Data augmentation (DA) has gained widespread popularity in deep speaker models due to
its ease of implementation and significant effectiveness. It enriches training data by …
its ease of implementation and significant effectiveness. It enriches training data by …
A Simple Unsupervised Knowledge-Free Domain Adaptation for Speaker Recognition
W Lin, L Li, D Wang - Applied Sciences, 2024 - mdpi.com
Despite the great success of speaker recognition models based on deep neural networks,
deploying a pre-trained model in real-world scenarios often leads to significant performance …
deploying a pre-trained model in real-world scenarios often leads to significant performance …
SE/BN Adapter: Parametric Efficient Domain Adaptation for Speaker Recognition
Deploying a well-optimized pre-trained speaker recognition model in a new domain often
leads to a significant decline in performance. While fine-tuning is a commonly employed …
leads to a significant decline in performance. While fine-tuning is a commonly employed …