Picture for Shuoyi Zhou

Shuoyi Zhou

VoxInstruct: Expressive Human Instruction-to-Speech Generation with Unified Multilingual Codec Language Modelling

Add code
Aug 28, 2024
Figure 1 for VoxInstruct: Expressive Human Instruction-to-Speech Generation with Unified Multilingual Codec Language Modelling
Figure 2 for VoxInstruct: Expressive Human Instruction-to-Speech Generation with Unified Multilingual Codec Language Modelling
Figure 3 for VoxInstruct: Expressive Human Instruction-to-Speech Generation with Unified Multilingual Codec Language Modelling
Figure 4 for VoxInstruct: Expressive Human Instruction-to-Speech Generation with Unified Multilingual Codec Language Modelling
Viaarxiv icon

The THU-HCSI Multi-Speaker Multi-Lingual Few-Shot Voice Cloning System for LIMMITS'24 Challenge

Add code
Apr 25, 2024
Viaarxiv icon