Liu Dongxu's starred repositories
GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
PaddleSpeech
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
DeepFilterNet
Noise supression using deep filtering
awesome-image-denoising-state-of-the-art
awesome image and video denoising, state of the art networks
sound-source-localization-algorithm_DOA_estimation
关于语音信号声源定位DOA估计所用的一些传统算法
FullSubNet-plus
The official PyTorch implementation of "FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement".
Spherical-Array-Processing
A collection of MATLAB routines for acoustical array processing on spherical harmonic signals, commonly captured with a spherical microphone array.
Cone-of-Silence
The Cone of Silence:
finetuning-scheduler
A PyTorch Lightning extension that accelerates and enhances foundation model experimentation with flexible fine-tuning schedules.
LearnableUpsamplingLayer-Pytorch
Pytorch implementation of LearnableUpsamplingLayer (NaturalSpeech, Tan et al., 2022)
CausalityCheck
Causality Check in Frame-online Speech Separation
Microphone-Array-Generalization-for-Multichannel-Narrowband-Deep-Speech-Enhancement
This is the microphone array generalization investigation based on previous Narrow Band Deep Filtering methods.
chime4-nn-mask
Implementation of NN based mask estimator in pytorch
anechoic-noise
Generator for anechoic, non-stationary noise signals
Generation-of-phase-only-hologram
Several methods of generating phase-only Fresnel hologram for representing a multiple depth object.
attentions
PyTorch implementation of some attentions for Deep Learning Researchers.