Picture for Heyang Xue

Heyang Xue

Multi-GradSpeech: Towards Diffusion-based Multi-Speaker Text-to-speech Using Consistent Diffusion Models

Add code
Aug 31, 2023
Figure 1 for Multi-GradSpeech: Towards Diffusion-based Multi-Speaker Text-to-speech Using Consistent Diffusion Models
Figure 2 for Multi-GradSpeech: Towards Diffusion-based Multi-Speaker Text-to-speech Using Consistent Diffusion Models
Viaarxiv icon

VISinger 2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizer

Add code
Nov 05, 2022
Figure 1 for VISinger 2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizer
Figure 2 for VISinger 2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizer
Figure 3 for VISinger 2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizer
Figure 4 for VISinger 2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizer
Viaarxiv icon

AdaVITS: Tiny VITS for Low Computing Resource Speaker Adaptation

Add code
Jun 01, 2022
Figure 1 for AdaVITS: Tiny VITS for Low Computing Resource Speaker Adaptation
Figure 2 for AdaVITS: Tiny VITS for Low Computing Resource Speaker Adaptation
Figure 3 for AdaVITS: Tiny VITS for Low Computing Resource Speaker Adaptation
Figure 4 for AdaVITS: Tiny VITS for Low Computing Resource Speaker Adaptation
Viaarxiv icon

Learn2Sing 2.0: Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher

Add code
Mar 30, 2022
Figure 1 for Learn2Sing 2.0: Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher
Figure 2 for Learn2Sing 2.0: Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher
Figure 3 for Learn2Sing 2.0: Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher
Figure 4 for Learn2Sing 2.0: Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher
Viaarxiv icon

Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis

Add code
Jan 20, 2022
Figure 1 for Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis
Figure 2 for Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis
Figure 3 for Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis
Figure 4 for Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis
Viaarxiv icon

VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis

Add code
Oct 17, 2021
Figure 1 for VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis
Figure 2 for VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis
Figure 3 for VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis
Figure 4 for VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis
Viaarxiv icon