Picture for Luwen Zhang

Luwen Zhang

SnakeGAN: A Universal Vocoder Leveraging DDSP Prior Knowledge and Periodic Inductive Bias

Add code
Sep 14, 2023
Viaarxiv icon

Joint Multi-scale Cross-lingual Speaking Style Transfer with Bidirectional Attention Mechanism for Automatic Dubbing

Add code
May 09, 2023
Viaarxiv icon

Content-Dependent Fine-Grained Speaker Embedding for Zero-Shot Speaker Adaptation in Text-to-Speech Synthesis

Add code
Apr 03, 2022
Figure 1 for Content-Dependent Fine-Grained Speaker Embedding for Zero-Shot Speaker Adaptation in Text-to-Speech Synthesis
Figure 2 for Content-Dependent Fine-Grained Speaker Embedding for Zero-Shot Speaker Adaptation in Text-to-Speech Synthesis
Figure 3 for Content-Dependent Fine-Grained Speaker Embedding for Zero-Shot Speaker Adaptation in Text-to-Speech Synthesis
Figure 4 for Content-Dependent Fine-Grained Speaker Embedding for Zero-Shot Speaker Adaptation in Text-to-Speech Synthesis
Viaarxiv icon