Zezhong Jin

5 papers · 2024–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11)

Venues

Interspeech (4) EMNLP (1)

Top co-authors

Man-Wai Mak (5) Zhe Li (3) Chong-Xin Gan (2) Youzhi Tu (2) Kong Aik Lee (1) Biyi Fang (1) Zilong Huang (1) Shujie LIU (1) Yan Lu (1) Zhuoyi Huang (1)

Research topics

Deep Learning (3) Machine Learning (2) Speech & Audio (2) Learning Types · Deep Learning (2) Learning Types · Machine Learning (2) Models (2) Analysis (1) Application Areas (1) Architectures (1) Core Methods (1) Recognition (1)

Keywords

speaker verification (4) speaker embedding (2) knowledge distillation (2) contrastive learning (2) representation disentanglement (1) transformer network (1) latent diffusion model (1) positional embedding (1) handwriting generation (1) non-contrastive dino (1) global view (1) ink generation (1) inter-speaker relation (1) intra-speaker relation (1) self-supervised learning (1) knowledge transfer (1) variational autoencoder (1)

Papers

Disentangling Speaker and Content in Pre-trained Speech Models with Latent Diffusion for Robust Speaker Verification Interspeech 2025 IDIR: Identifying and Distilling Informative Relations for Speaker Verification Interspeech 2025 TrInk: Ink Generation with Transformer Network EMNLP 2025 Self-Supervised Learning with Multi-Head Multi-Mode Knowledge Distillation for Speaker Verification Interspeech 2024 W-GVKT: Within-Global-View Knowledge Transfer for Speaker Verification Interspeech 2024