Picture for Yuguang Yang

Yuguang Yang

Fine-grained Preference Optimization Improves Zero-shot Text-to-Speech

Add code
Feb 05, 2025
Viaarxiv icon

StableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matching

Add code
Dec 10, 2024
Viaarxiv icon

CTEFM-VC: Zero-Shot Voice Conversion Based on Content-Aware Timbre Ensemble Modeling and Flow Matching

Add code
Nov 04, 2024
Viaarxiv icon

Takin-ADA: Emotion Controllable Audio-Driven Animation with Canonical and Landmark Loss Optimization

Add code
Oct 18, 2024
Viaarxiv icon

Takin-VC: Zero-shot Voice Conversion via Jointly Hybrid Content and Memory-Augmented Context-Aware Timbre Modeling

Add code
Oct 02, 2024
Figure 1 for Takin-VC: Zero-shot Voice Conversion via Jointly Hybrid Content and Memory-Augmented Context-Aware Timbre Modeling
Figure 2 for Takin-VC: Zero-shot Voice Conversion via Jointly Hybrid Content and Memory-Augmented Context-Aware Timbre Modeling
Figure 3 for Takin-VC: Zero-shot Voice Conversion via Jointly Hybrid Content and Memory-Augmented Context-Aware Timbre Modeling
Figure 4 for Takin-VC: Zero-shot Voice Conversion via Jointly Hybrid Content and Memory-Augmented Context-Aware Timbre Modeling
Viaarxiv icon

Takin: A Cohort of Superior Quality Zero-shot Speech Generation Models

Add code
Sep 18, 2024
Viaarxiv icon

MUSA: Multi-lingual Speaker Anonymization via Serial Disentanglement

Add code
Jul 16, 2024
Figure 1 for MUSA: Multi-lingual Speaker Anonymization via Serial Disentanglement
Figure 2 for MUSA: Multi-lingual Speaker Anonymization via Serial Disentanglement
Figure 3 for MUSA: Multi-lingual Speaker Anonymization via Serial Disentanglement
Figure 4 for MUSA: Multi-lingual Speaker Anonymization via Serial Disentanglement
Viaarxiv icon

DecomCAM: Advancing Beyond Saliency Maps through Decomposition and Integration

Add code
May 29, 2024
Viaarxiv icon

GMP-ATL: Gender-augmented Multi-scale Pseudo-label Enhanced Adaptive Transfer Learning for Speech Emotion Recognition via HuBERT

Add code
May 03, 2024
Viaarxiv icon

PP-MeT: a Real-world Personalized Prompt based Meeting Transcription System

Add code
Sep 28, 2023
Figure 1 for PP-MeT: a Real-world Personalized Prompt based Meeting Transcription System
Figure 2 for PP-MeT: a Real-world Personalized Prompt based Meeting Transcription System
Figure 3 for PP-MeT: a Real-world Personalized Prompt based Meeting Transcription System
Figure 4 for PP-MeT: a Real-world Personalized Prompt based Meeting Transcription System
Viaarxiv icon