Publications

Learning to Behave Like Clean Speech: Dual-Branch Knowledge Distillation for Noise-Robust Fake Audio Detection.

An overview of affective speech synthesis and conversion in the deep learning era

Adversarial multi-task learning for mandarin prosodic boundary prediction with multi-modal embeddings

Add 2023: the second audio deepfake detection challenge

Adaptive fake audio detection with low-rank model squeezing

Method and apparatus for editing audio, electronic device and storage medium

Text Enhancement for Paragraph Processing in End-to-End Code-switching TTS

System fingerprint recognition for deepfake audio: An initial dataset and investigation

Singing-Tacotron: Global duration control attention and dynamic filter for end-to-end singing voice synthesis

Neuraldps: Neural deterministic plus stochastic model with multiband excitation for noise-controllable waveform generation