Picture for Qicong Xie

Qicong Xie

MSM-VC: High-fidelity Source Style Transfer for Non-Parallel Voice Conversion by Multi-scale Style Modeling

Add code
Sep 03, 2023
Figure 1 for MSM-VC: High-fidelity Source Style Transfer for Non-Parallel Voice Conversion by Multi-scale Style Modeling
Figure 2 for MSM-VC: High-fidelity Source Style Transfer for Non-Parallel Voice Conversion by Multi-scale Style Modeling
Figure 3 for MSM-VC: High-fidelity Source Style Transfer for Non-Parallel Voice Conversion by Multi-scale Style Modeling
Figure 4 for MSM-VC: High-fidelity Source Style Transfer for Non-Parallel Voice Conversion by Multi-scale Style Modeling
Viaarxiv icon

UniSyn: An End-to-End Unified Model for Text-to-Speech and Singing Voice Synthesis

Add code
Dec 06, 2022
Figure 1 for UniSyn: An End-to-End Unified Model for Text-to-Speech and Singing Voice Synthesis
Figure 2 for UniSyn: An End-to-End Unified Model for Text-to-Speech and Singing Voice Synthesis
Figure 3 for UniSyn: An End-to-End Unified Model for Text-to-Speech and Singing Voice Synthesis
Figure 4 for UniSyn: An End-to-End Unified Model for Text-to-Speech and Singing Voice Synthesis
Viaarxiv icon

Expressive-VC: Highly Expressive Voice Conversion with Attention Fusion of Bottleneck and Perturbation Features

Add code
Nov 09, 2022
Figure 1 for Expressive-VC: Highly Expressive Voice Conversion with Attention Fusion of Bottleneck and Perturbation Features
Figure 2 for Expressive-VC: Highly Expressive Voice Conversion with Attention Fusion of Bottleneck and Perturbation Features
Figure 3 for Expressive-VC: Highly Expressive Voice Conversion with Attention Fusion of Bottleneck and Perturbation Features
Figure 4 for Expressive-VC: Highly Expressive Voice Conversion with Attention Fusion of Bottleneck and Perturbation Features
Viaarxiv icon

Cross-speaker Emotion Transfer Based On Prosody Compensation for End-to-End Speech Synthesis

Add code
Jul 04, 2022
Figure 1 for Cross-speaker Emotion Transfer Based On Prosody Compensation for End-to-End Speech Synthesis
Figure 2 for Cross-speaker Emotion Transfer Based On Prosody Compensation for End-to-End Speech Synthesis
Figure 3 for Cross-speaker Emotion Transfer Based On Prosody Compensation for End-to-End Speech Synthesis
Figure 4 for Cross-speaker Emotion Transfer Based On Prosody Compensation for End-to-End Speech Synthesis
Viaarxiv icon

End-to-End Voice Conversion with Information Perturbation

Add code
Jun 15, 2022
Figure 1 for End-to-End Voice Conversion with Information Perturbation
Figure 2 for End-to-End Voice Conversion with Information Perturbation
Figure 3 for End-to-End Voice Conversion with Information Perturbation
Figure 4 for End-to-End Voice Conversion with Information Perturbation
Viaarxiv icon

Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios

Add code
Dec 23, 2021
Figure 1 for Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios
Figure 2 for Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios
Figure 3 for Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios
Figure 4 for Multi-speaker Multi-style Text-to-speech Synthesis With Single-speaker Single-style Training Data Scenarios
Viaarxiv icon

One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation

Add code
Nov 24, 2021
Viaarxiv icon

Controllable cross-speaker emotion transfer for end-to-end speech synthesis

Add code
Sep 14, 2021
Figure 1 for Controllable cross-speaker emotion transfer for end-to-end speech synthesis
Figure 2 for Controllable cross-speaker emotion transfer for end-to-end speech synthesis
Figure 3 for Controllable cross-speaker emotion transfer for end-to-end speech synthesis
Figure 4 for Controllable cross-speaker emotion transfer for end-to-end speech synthesis
Viaarxiv icon

AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person

Add code
Aug 11, 2021
Figure 1 for AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person
Figure 2 for AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person
Figure 3 for AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person
Figure 4 for AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person
Viaarxiv icon

The Multi-speaker Multi-style Voice Cloning Challenge 2021

Apr 05, 2021
Figure 1 for The Multi-speaker Multi-style Voice Cloning Challenge 2021
Figure 2 for The Multi-speaker Multi-style Voice Cloning Challenge 2021
Viaarxiv icon