Chuyuan Zhang — accepted AI-conference papers

2025

Adversarial Training and Gradient Optimization for Partially Deepfake Audio Localization

Siding Zeng, Jiangyan Yi, Jianhua Tao, Jiayi He, Zheng Lian, Shan Liang +3

ICASSP 2025accepted

Partially deepfake audio localization is important in audio forensics. However, existing localization models for partially deepfake audio face two major challenges: distribution shifts between training and testing data as well as insufficient utilization of information from both manipulated regions…

Cited by 0 Source ↗Scholar ↗

2025

WMCodec: End-to-End Neural Speech Codec with Deep Watermarking for Authenticity Verification

Junzuo Zhou, Jiangyan Yi, Yong Ren, Jianhua Tao, Tao Wang, Chuyuan Zhang

ICASSP 2025accepted

Recent advances in speech spoofing necessitate stronger verification mechanisms in neural speech codecs to ensure authenticity. Current methods embed numerical watermarks before compression and extract them from reconstructed speech for verification, but face limitations such as separate training pr…

Cited by 0 Source ↗Scholar ↗