Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis
Paper • 2502.04128 • Published • 27
ZhenYE
ZhenYe234
AI & ML interests
None yet
Recent Activity
upvoted a paper about 6 hours ago
Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling liked a dataset 4 months ago
jjuik2014/DH-FaceVid-1K liked a model 7 months ago
Atotti/Qwen3-Omni-AudioTransformerOrganizations
authored 5
papers over 1 year ago
CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model
Paper • 2305.06908 • Published • 7
CoMoSVC: Consistency Model-based Singing Voice Conversion
Paper • 2401.01792 • Published • 11
FlashSpeech: Efficient Zero-Shot Speech Synthesis
Paper • 2404.14700 • Published • 32
Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model
Paper • 2408.17175 • Published • 6