Scholar
Zexin Cai
Google Scholar ID: ZwXs7rsAAAAJ
Johns Hopkins University
speech signal processing
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
429
H-index
13
i10-index
16
Publications
20
Co-authors
0
Contact
Email
zcai21@jhu.edu
GitHub
Open ↗
LinkedIn
Open ↗
Publications
9 items
Brain2Speech-Net: Intelligible, Real-Time Brain-to-Speech Synthesis Without Text Decoding
2026
Cited
0
DiffAnon: Diffusion-based Prosody Control for Voice Anonymization
2026
Cited
0
Integrated Spoofing-Robust Automatic Speaker Verification via a Three-Class Formulation and LLR
2026
Cited
0
Can LLMs Help Localize Fake Words in Partially Fake Speech?
2026
Cited
0
Universal Speech Content Factorization
2026
Cited
0
Content Anonymization for Privacy in Long-form Audio
2025
Cited
0
Less is More for Synthetic Speech Detection in the Wild
2025
Cited
0
GenVC: Self-Supervised Zero-Shot Voice Conversion
2025
Cited
0
Load more
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)
