Wenzhe Liu (刘文哲)'s Projects
Machine and Deep Learning models for speech dereverberation
Instant voice cloning by MyShell.
Psychoacoustic Calibration for Efficient Neural Audio Coding
(Work In Progress) Unofficial implementation of PercepNet: A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech
percepnet implemented using Keras, still need to be optimized and tuned.
simple and efficient python implemention of a series of adaptive filters (lms、nlms、rls、kalman、Frequency Domain Adaptive Filter、Partitioned-Block-Based Frequency Domain Adaptive Filter、Frequency Domain Kalman Filter、Partitioned-Block-Based Frequency Domain Kalman Filter) for acoustic echo cancellation.
Pyroomacoustics is a package for audio signal processing for indoor applications. It was developed as a fast prototyping platform for beamforming algorithms in indoor scenarios.
A Python example For Acoustic Howling Suppression
A temporal module for PyTorch-ComplexTensor
Fork on origin rnnoise
Agora Solo is an open source speech codec, it was developed based on Silk with BWE(Bandwidth Extension) and MDC(Multi Description Coding). With these technologies, Solo is enable to resist weak networks at low bitrates.
关于语音信号声源定位DOA估计所用的一些传统算法
The reproduced code for Google's SoundStorm
This repository is an implementation of this article: https://arxiv.org/pdf/2107.03312.pdf
List of speech synthesis papers.
A Temporal-Spectral Generative Adversarial Network based End-to-end Packet Loss Concealment for Wideband Speech Transmission
Source code for Twitter's Recommendation Algorithm
Pytorch implementation of subband decomposition
TTS FrontEnd DataSet: Polyphone / Prosody / TextNormalization
This repo summarizes the tutorials, datasets, papers, codes and tools for speech separation and speaker extraction task. You are kindly invited to pull requests.
PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html
Vector Quantization, in Pytorch
A software that supports real time video&audio processing for meeting application.
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
webrtc audio processing