4 papers
LoOPSD: On-Policy Self-Distillation with Looped Teachers
Wei Fan, Qingyue Yang, Chao-Hong Tan +6
On-policy self-distillation improves a model using guidance from the model itself, but it still requires a teacher that provides more useful predictions than the student. Existing…
BareWave: Waveform-Native Flow-Matching Text-to-Speech
Wei Fan, Chao-Hong Tan, Qian Chen +5
Removing intermediate representations and separately trained decoding stages has become an important direction in generative modeling. In text-to-speech, however, high-quality syst…
WavInWav: Time-domain Speech Hiding via Invertible Neural Network
Wei Fan, Kejiang Chen, Xiangkun Wang +2
Data hiding is essential for secure communication across digital media, and recent advances in Deep Neural Networks (DNNs) provide enhanced methods for embedding secret information…
De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning Attacks
Wei Fan, Kejiang Chen, Chang Liu +2
The rapid advancement of speech generation models has heightened privacy and security concerns related to voice cloning (VC). Recent studies have investigated disrupting unauthoriz…