Picture for Gyuhyeon Nam

Gyuhyeon Nam

Improving Robustness of Diffusion-Based Zero-Shot Speech Synthesis via Stable Formant Generation

Add code
Sep 14, 2024
Figure 1 for Improving Robustness of Diffusion-Based Zero-Shot Speech Synthesis via Stable Formant Generation
Figure 2 for Improving Robustness of Diffusion-Based Zero-Shot Speech Synthesis via Stable Formant Generation
Figure 3 for Improving Robustness of Diffusion-Based Zero-Shot Speech Synthesis via Stable Formant Generation
Figure 4 for Improving Robustness of Diffusion-Based Zero-Shot Speech Synthesis via Stable Formant Generation
Viaarxiv icon

Good Neighbors Are All You Need for Chinese Grapheme-to-Phoneme Conversion

Add code
Mar 14, 2023
Figure 1 for Good Neighbors Are All You Need for Chinese Grapheme-to-Phoneme Conversion
Figure 2 for Good Neighbors Are All You Need for Chinese Grapheme-to-Phoneme Conversion
Figure 3 for Good Neighbors Are All You Need for Chinese Grapheme-to-Phoneme Conversion
Figure 4 for Good Neighbors Are All You Need for Chinese Grapheme-to-Phoneme Conversion
Viaarxiv icon

KoDF: A Large-scale Korean DeepFake Detection Dataset

Add code
Mar 18, 2021
Figure 1 for KoDF: A Large-scale Korean DeepFake Detection Dataset
Figure 2 for KoDF: A Large-scale Korean DeepFake Detection Dataset
Figure 3 for KoDF: A Large-scale Korean DeepFake Detection Dataset
Figure 4 for KoDF: A Large-scale Korean DeepFake Detection Dataset
Viaarxiv icon

GAN Vocoder: Multi-Resolution Discriminator Is All You Need

Add code
Mar 09, 2021
Figure 1 for GAN Vocoder: Multi-Resolution Discriminator Is All You Need
Figure 2 for GAN Vocoder: Multi-Resolution Discriminator Is All You Need
Figure 3 for GAN Vocoder: Multi-Resolution Discriminator Is All You Need
Figure 4 for GAN Vocoder: Multi-Resolution Discriminator Is All You Need
Viaarxiv icon

Axial Residual Networks for CycleGAN-based Voice Conversion

Add code
Mar 08, 2021
Figure 1 for Axial Residual Networks for CycleGAN-based Voice Conversion
Figure 2 for Axial Residual Networks for CycleGAN-based Voice Conversion
Figure 3 for Axial Residual Networks for CycleGAN-based Voice Conversion
Figure 4 for Axial Residual Networks for CycleGAN-based Voice Conversion
Viaarxiv icon