Zhengqi Wen

The codecfake dataset and countermeasures for the universally detection of deepfake audio

Neural Codec Source Tracing: Toward Comprehensive Attribution in Open-Set Condition

MTPareto: A MultiModal Targeted Pareto Framework for Fake News Detection

Mixture of experts fusion for fake audio detection using frozen wav2vec 2.0

DPI-TTS: Directional Patch Interaction for Fast-Converging and Style Temporal Modeling in Text-to-Speech

VQ-CTAP: Cross-Modal Fine-Grained Sequence Representation Learning for Speech Processing

Unlocking the Power of Emotions: Enhancing Personality Trait Recognition Through Utilization of Emotional Cues

Transferring Personality Knowledge to Multimodal Sentiment Analysis

Text Prompt is Not Enough: Sound Event Enhanced Prompt Adapter for Target Style Audio Generation

Temporal Variability and Multi-Viewed Self-Supervised Representations to Tackle the ASVspoof5 Deepfake Challenge