Litcius/Paper detail

Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker Adaptation

Ha-Yeong Choi, Sang-Hoon Lee, Seong–Whan Lee

202331 citationsDOI

Topics & Concepts

Adaptation (eye)Zero (linguistics)Speech recognitionComputer scienceDiffusionShot (pellet)PhysicsMaterials scienceOpticsLinguisticsThermodynamicsMetallurgyPhilosophySpeech Recognition and SynthesisSpeech and Audio ProcessingMusic and Audio Processing
Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker Adaptation | Litcius