conftrace_

one-step sampling

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

diffusion model (2) speaker style preservation (1) pseudo-huber loss (1) video fusion (1) fid score (1) content encoder (1) learned prior (1) zero-shot speech synthesis (1) zero-shot voice cloning (1) speech generation (1)

Papers

Streaming Diffusion Model for Fast Infrared and Visible Video Fusion CVPR 2026 FasterVoiceGrad: Faster One-step Diffusion-Based Voice Conversion with Adversarial Diffusion Conversion Distillation Interspeech 2025 OZSpeech: One-step Zero-shot Speech Synthesis with Learned-Prior-Conditioned Flow Matching ACL 2025 Improved Techniques for Training Consistency Models ICLR 2024