Picture for Chunhui Wang

Chunhui Wang

HAM-TTS: Hierarchical Acoustic Modeling for Token-Based Zero-Shot Text-to-Speech with Model and Data Scaling

Mar 09, 2024
Figure 1 for HAM-TTS: Hierarchical Acoustic Modeling for Token-Based Zero-Shot Text-to-Speech with Model and Data Scaling
Figure 2 for HAM-TTS: Hierarchical Acoustic Modeling for Token-Based Zero-Shot Text-to-Speech with Model and Data Scaling
Figure 3 for HAM-TTS: Hierarchical Acoustic Modeling for Token-Based Zero-Shot Text-to-Speech with Model and Data Scaling
Figure 4 for HAM-TTS: Hierarchical Acoustic Modeling for Token-Based Zero-Shot Text-to-Speech with Model and Data Scaling
Viaarxiv icon

CrossSinger: A Cross-Lingual Multi-Singer High-Fidelity Singing Voice Synthesizer Trained on Monolingual Singers

Add code
Sep 22, 2023
Viaarxiv icon

A Fast and Lightweight Network for Low-Light Image Enhancement

Add code
Apr 06, 2023
Figure 1 for A Fast and Lightweight Network for Low-Light Image Enhancement
Figure 2 for A Fast and Lightweight Network for Low-Light Image Enhancement
Figure 3 for A Fast and Lightweight Network for Low-Light Image Enhancement
Figure 4 for A Fast and Lightweight Network for Low-Light Image Enhancement
Viaarxiv icon

Xiaoicesing 2: A High-Fidelity Singing Voice Synthesizer Based on Generative Adversarial Network

Add code
Oct 28, 2022
Figure 1 for Xiaoicesing 2: A High-Fidelity Singing Voice Synthesizer Based on Generative Adversarial Network
Figure 2 for Xiaoicesing 2: A High-Fidelity Singing Voice Synthesizer Based on Generative Adversarial Network
Figure 3 for Xiaoicesing 2: A High-Fidelity Singing Voice Synthesizer Based on Generative Adversarial Network
Viaarxiv icon

HiFi-WaveGAN: Generative Adversarial Network with Auxiliary Spectrogram-Phase Loss for High-Fidelity Singing Voice Generation

Add code
Oct 26, 2022
Figure 1 for HiFi-WaveGAN: Generative Adversarial Network with Auxiliary Spectrogram-Phase Loss for High-Fidelity Singing Voice Generation
Figure 2 for HiFi-WaveGAN: Generative Adversarial Network with Auxiliary Spectrogram-Phase Loss for High-Fidelity Singing Voice Generation
Figure 3 for HiFi-WaveGAN: Generative Adversarial Network with Auxiliary Spectrogram-Phase Loss for High-Fidelity Singing Voice Generation
Figure 4 for HiFi-WaveGAN: Generative Adversarial Network with Auxiliary Spectrogram-Phase Loss for High-Fidelity Singing Voice Generation
Viaarxiv icon

A Simple Self-calibration Method for The Internal Time Synchronization of MEMS LiDAR

Sep 26, 2021
Figure 1 for A Simple Self-calibration Method for The Internal Time Synchronization of MEMS LiDAR
Figure 2 for A Simple Self-calibration Method for The Internal Time Synchronization of MEMS LiDAR
Figure 3 for A Simple Self-calibration Method for The Internal Time Synchronization of MEMS LiDAR
Figure 4 for A Simple Self-calibration Method for The Internal Time Synchronization of MEMS LiDAR
Viaarxiv icon

Self-supervised Low Light Image Enhancement and Denoising

Mar 01, 2021
Figure 1 for Self-supervised Low Light Image Enhancement and Denoising
Figure 2 for Self-supervised Low Light Image Enhancement and Denoising
Figure 3 for Self-supervised Low Light Image Enhancement and Denoising
Figure 4 for Self-supervised Low Light Image Enhancement and Denoising
Viaarxiv icon

Better Than Reference In Low Light Image Enhancement: Conditional Re-Enhancement Networks

Add code
Aug 26, 2020
Figure 1 for Better Than Reference In Low Light Image Enhancement: Conditional Re-Enhancement Networks
Figure 2 for Better Than Reference In Low Light Image Enhancement: Conditional Re-Enhancement Networks
Figure 3 for Better Than Reference In Low Light Image Enhancement: Conditional Re-Enhancement Networks
Figure 4 for Better Than Reference In Low Light Image Enhancement: Conditional Re-Enhancement Networks
Viaarxiv icon

Self-supervised Image Enhancement Network: Training with Low Light Images Only

Add code
Feb 26, 2020
Figure 1 for Self-supervised Image Enhancement Network: Training with Low Light Images Only
Figure 2 for Self-supervised Image Enhancement Network: Training with Low Light Images Only
Figure 3 for Self-supervised Image Enhancement Network: Training with Low Light Images Only
Figure 4 for Self-supervised Image Enhancement Network: Training with Low Light Images Only
Viaarxiv icon