cập nhật 47 phút trước
24
VoxMel TTS Technical Report
📄 Paper HF Daily Papers 3 ngày trước

Continuous autoregressive TTS relies on an acoustic target that enables stable next-latent modeling while preserving fine-grained acoustic details. While existing approaches employ learned compressed representations (e.g., continuous VAE latents) to render prediction tractable, t…

🅲 hạng C