Hong Kong
YE Zhen
Elite@zhenye234
Speech synthesis, Audio generation, Speech LLM
LLaSA_training. LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis
661X-Codec-2.0. Codec for paper: LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis
360xcodec. AAAI 2025: Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model
308CoMoSpeech. ACM MM 2023 CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model
214FlashSpeech. ACM MM 2024 FlashSpeech: Efficient Zero-Shot Speech Synthesis
155Talker-T2AV. ACM MM 2026 Talker-T2AV Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling
77LLaSA_inference.
43 views 7 projects
Apply