9 papers
Toward Interpretable Speech Deepfake Detection using Artifact-Specific Experts and Calibrated Detection Scores
Viola Negroni, Xin Wang, Wanying Ge +3
In this work, we propose an interpretable framework for speech deepfake detection based on artifact-specific expert models. Rather than relying on black-box decisions, the framewor…
Self Voice Conversion as an Attack against Neural Audio Watermarking
Yigitcan Ãzer, Wanying Ge, Zhe Zhang +2
Audio watermarking embeds auxiliary information into speech while maintaining speaker identity, linguistic content, and perceptual quality. Although recent advances in neural and d…
Does Fine-tuning by Reinforcement Learning Improve Generalization in Binary Speech Deepfake Detection?
Xin Wang, Ge Wanying, Junichi Yamagishi
Building speech deepfake detection models that are generalizable to unseen attacks remains a challenging problem. Although the field has shifted toward a pre-training and fine-tuni…
Deepfake Word Detection by Next-token Prediction using Fine-tuned Whisper
Hoan My Tran, Xin Wang, Wanying Ge +2
Deepfake speech utterances can be forged by replacing one or more words in a bona fide utterance with semantically different words synthesized with speech-generative models. While…
Post-training for Deepfake Speech Detection
Wanying Ge, Xin Wang, Xuechen Liu +1
We introduce a post-training approach that adapts self-supervised learning (SSL) models for deepfake speech detection by bridging the gap between general pre-training and domain-sp…
FakeMark: Deepfake Speech Attribution With Watermarked Artifacts
Wanying Ge, Xin Wang, Junichi Yamagishi
Deepfake speech attribution remains challenging for existing solutions. Classifier-based solutions often fail to generalize to domain-shifted samples, and watermarking-based soluti…