Jian-Tao Zhang — accepted AI-conference papers

2024

Meta Representation Learning Method for Robust Speaker Verification in Unseen Domains

Jian-Tao Zhang, Yan Song, Jin Li, Wu Guo, Hao-Yu Song, Ian McLoughlin

ICASSP 2024accepted

This paper presents a meta representation learning method for robust speaker verification (SV) in unseen domains. It is known that the existing embedding learning based SV systems may suffer from domain mismatch issues. To address this, we propose an episodic training procedure to compensate domain…

Cited by 0 Source ↗Scholar ↗

2023

Stargan-vc Based Cross-Domain Data Augmentation for Speaker Verification

Hang-Rui Hu, Yan Song, Jian-Tao Zhang, Li-Rong Dai, Ian McLoughlin, Zhu Zhuo +3

ICASSP 2023accepted

Automatic speaker verification (ASV) faces domain shift caused by the mismatch of intrinsic and extrinsic factors, such as recording device and speaking style, in real-world applications, which leads to severe performance degradation. Since single-speaker multi-condition (SSMC) data is difficult to…

Cited by 0 Source ↗Scholar ↗