Tacit-TTS: From Autoregressive Decoding to Masked Prediction for Efficient Transcript-Free Voice Cloning
Paper • 2609.38658 • Published • 14
You Zhang
yzyouzhang
·
AI & ML interests
Audio-visual rendering and analysis, voice anti-spoofing, spatial audio
Recent Activity
upvoted a paper 7 months ago
Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression liked a model 7 months ago
HumeAI/tada-1bOrganizations
upvoted a paper 20 days ago