Yuancheng Wang

SpeechJudge: Towards Human-Level Judgment for Speech Naturalness

Scaling Speech Tokenizers with Diffusion Autoencoders

FlexiVoice: Enabling Flexible Style Control in Zero-Shot TTS with Natural Language Instructions

Metis: A Foundation Speech Generation Model with Masked Generative Pre-training

TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling

FOLEYCRAFTER: BRING SILENT VIDEOS TO LIFE WITH LIFELIKE AND SYNCHRONIZED SOUNDS

MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer

RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis