Optimal Transport with Class Structure Exploration for Cross-Domain Speech Emotion Recognition

R Zhang, J Wei, X Lu, J Xu, Y Li, D **… - … on Audio, Speech …, 2024 - ieeexplore.ieee.org
Speech emotion recognition (SER) has widespread applications in human-computer
interaction. However, the performance of SER models often drops in domain mismatch …

Unsupervised adaptive speaker recognition by coupling-regularized optimal transport

R Zhang, J Wei, X Lu, W Lu, D **… - … /ACM Transactions on …, 2024 - ieeexplore.ieee.org
Cross-domain speaker recognition (SR) can be improved by unsupervised domain
adaptation (UDA) algorithms. UDA algorithms often reduce domain mismatch at the cost of …

Self-distillation-based domain exploration for source speaker verification under spoofed speech from unknown voice conversion

X Ma, R Zhang, J Wei, X Lu, J Xu, L Zhang, W Lu - Speech Communication, 2025 - Elsevier
Advancements in voice conversion (VC) technology have made it easier to generate
spoofed speech that closely resembles the identity of a target speaker. Meanwhile …

Self-Supervised Domain Exploration with an Optimal Transport Regularization for Open Set Cross-Domain Speech Emotion Recognition

R Zhang, J Wei, X Lu, Y Li, W Lu… - ICASSP 2024-2024 …, 2024 - ieeexplore.ieee.org
In the tasks of domain adaptation (DA) for speech emotion recognition (SER), self-
supervised learning (SSL) algorithms could effectively explore domain and structural …