Deep Learning | Speech Synthesis | Neural Vocoder
-
42dot Inc.
- Seoul, Korea
- https://scholar.google.com/citations?authuser=1&user=d3VX0zQAAAAJ
Highlights
- Pro
Stars
5
stars
written in Python
Clear filter
AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss
A Non-Autoregressive Text-to-Speech (NAR-TTS) framework, including official PyTorch implementation of PortaSpeech (NeurIPS 2021) and DiffSpeech (AAAI 2022)
Official Pytorch Implementation of "Diff-HierVC: Diffusion-based Hierarchical Voice Conversion with Robust Pitch Generation and Masked Prior for Zero-shot Speaker Adaptation"