ZhaZhaFon's repositories
demo-speakerseparation
This is a demo for my bachelor thesis 'Speaker Separation and Machine Auditory Perception for Dialogue Scene'.
repo_voxcelebtrainer
说话人识别仓库-说话人表征-ResNet/VGGVox || a ready-to-use repo for Speaker Verification / Speaker Embedding with xvector
repo_spectralclustering
说话人分割仓库-聚类分割-谱聚类 || a ready-to-use repo for Speaker Diariazation with Spectral Clustering
beautiful-jekyll
✨ Build a beautiful and simple website in literally minutes. Demo at https://beautifuljekyll.com
ECAPA-TDNN
Unofficial reimplementation of ECAPA-TDNN for speaker recognition (EER=0.86 for Vox1_O when train only in Vox2)
espnet
End-to-End Speech Processing Toolkit
kaldiio
A pure python module for reading and writing kaldi ark files
missing-semester-cn.github.io
the CS missing semester Chinese version
multi-speaker-tacotron
VCTK multi-speaker tacotron for ICASSP 2020
os_course_info
OS Lectures 2022 Spring in Dept. CS, Tsinghua Univ.
ParallelWaveGAN
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
pytorch-loss
label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful
repo_asteroid
语音前端仓库 || a modified version of Asteroid toolkit for Speech Front-end
repo_dvector
说话人识别仓库-说话人表征-dvector || a ready-to-use repo for Speaker Verification / Speaker Embedding with dvector
repo_librimix
An open source dataset for source separation
silero-vad
Silero VAD: pre-trained enterprise-grade Voice Activity Detector, Language Classifier and Spoken Number Detector
speaker_extraction_config
target speaker extraction and verification for multi-talker speech
Speech-Resources
语音方向实验室/公司/资源/实习等，欢迎推荐或自荐（排名不分先后）
speechbrain_config
A PyTorch-based Speech Toolkit
SpeechSplit
Unsupervised Speech Decomposition Via Triple Information Bottleneck
TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
voice_datasets
🔊 A comprehensive list of open-source datasets for voice and sound computing (95+ datasets).
voicesplit_config
VoiceSplit: Targeted Voice Separation by Speaker-Conditioned Spectrogram
voxceleb_unsupervised
Augmentation adversarial training for self-supervised speaker recognition