wenzheliu-speech Goto Github PK

followers: 263.0 following: 187.0 repos: 63.0 gists: 0.0

Name: Wenzhe Liu (刘文哲)

Type: User

Bio: Hi, I am Wenzhe Liu. I work for Kuaishou, and was employed by Tencent. focusing on generalized speech enhancement, audio codec and speech synthesis

Location: Beijing, China

Blog: https://wenzheliu-speech.github.io/

Hi, I'm Wenzhe Liu (刘文哲)

🏠 I work for Kuaishou(快手), and was employed by Tencent(腾讯), and graduated from the Institute of Acoustics, Chinese Academy of Sciences (中科院声学所)
📕 Research interests: speech enhancement, compression, synthesis, and voice conversion
- frontend processing: acoustic echo cancellation, denoising, and dereverberation
- audio codec and speech compression: audio (speech, music, and noise) codec, packet loss concealment, and bandwidth extension
- speech synthesis: TTS, voice conversion, and speech restoration
- far-field sound pickup: beamforming, DOA estimation, and microphone array signal processing
📫 How to reach me: [email protected]
More information about me on my homepage: https://wenzheliu-speech.github.io/

Wenzhe Liu (刘文哲)'s Projects

neural-speech-dereverberation

Machine and Deep Learning models for speech dereverberation

pam-nac

Psychoacoustic Calibration for Efficient Neural Audio Coding

percepnet

(Work In Progress) Unofficial implementation of PercepNet: A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech

percepnet-keras

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

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.

python_howling_suppression

A Python example For Acoustic Howling Suppression

pytorch_complex

A temporal module for PyTorch-ComplexTensor

realtime_audiodenoise_echocancellation

rnnoise

Fork on origin rnnoise

solo

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.

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

soundstorm

The reproduced code for Google's SoundStorm

soundstream

This repository is an implementation of this article: https://arxiv.org/pdf/2107.03312.pdf

speech-synthesis-paper

List of speech synthesis papers.

tfgan-plc

A Temporal-Spectral Generative Adversarial Network based End-to-end Packet Loss Concealment for Wideband Speech Transmission

the-algorithm

Source code for Twitter's Recommendation Algorithm

the-guidebook-of-speech-enhancement

tinyneuralnetwork

torchsubband

Pytorch implementation of subband decomposition

tts-frontend-dataset

TTS FrontEnd DataSet: Polyphone / Prosody / TextNormalization

tutorial_separation

This repo summarizes the tutorials, datasets, papers, codes and tools for speech separation and speaker extraction task. You are kindly invited to pull requests.

vall-e

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html

vector-quantize-pytorch

Vector Quantization, in Pytorch

video_conference_enhancer

A software that supports real time video&audio processing for meeting application.

vocos

Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

webrtc-audio-processing

webrtc audio processing

wenzheliu-speech Goto Github PK

Wenzhe Liu (刘文哲)'s Projects

Recommend Projects

Recommend Topics

Recommend Org