Kaizhi Qian

autovc. AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss

SpeechSplit. Unsupervised Speech Decomposition Via Triple Information Bottleneck

contentvec. speech self-supervised representations

AutoPST. Global Rhythm Style Transfer Without Text Transcriptions

WaveNet-Enhancement. Speech Enhancement using Bayesian WaveNet

deepbeam. Deep learning based Speech Beamforming

ProsodyLM. ProsodyLM: Uncovering the Emerging Prosody Processing Capabilities in Speech Language Models

SpeechSplit-Demo. Unsupervised Speech Decomposition via Triple Information Bottleneck

fast-wavenet. Efficient implementation of Wavenet generation.

autovc-demo. AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss

AutoPST-Demo. CSS

FFTNet. Pytorch Implementation of FFTNet

espeak-ng. eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.

ProsodyLM-Demo. HTML