zhongshijun Goto Github PK

speex-aec-matlab

Ported Speex AEC mdf algorithm from C to Matlab

sr_for_inroom_comm

Speech Reinforcement for In-Room Communications

styletalk

subband-music-separation

Pytorch: Channel-wise subband (CWS) input for better voice and accompaniment separation

subband_kalman_aec

Subband kalman filter for echo cancellation

subcnn

Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection

surveillance-video-system

a matlab surveillance video system

synctalk

[CVPR 2024] This is the official source for our paper "SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis"

tacotron-pytorch

Pytorch implementation of Tacotron

tacotron2

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

tacotron2-pytorch

Yet another PyTorch implementation of Tacotron 2 with reduction factor and faster training speed.

talkshow

This is the official repository for TalkSHOW: Generating Holistic 3D Human Motion from Speech [CVPR2023].

taploss

tasnet

A PyTorch implementation of Time-domain Audio Separation Network (TasNet) with Permutation Invariant Training (PIT) for speech separation.

tbd-evaluation

MATLAB toolbox to evaluate a new set of metrics in tracking-by-detection methods

tcn-beat-tracker-pytorch

PyTorch implementation of "Temporal convolutional networks for musical audio beat tracking"

tensorflow-gans

各类GAN综合在一起，借鉴了hwalsuklee大神的

test

这是个测试项目

the-gan-zoo

A list of all named GANs!

tinyrecurrentunet

Real-Time De-noising and De-reverbing with Tiny Recurrent UNet

tnn

TNN：由腾讯优图实验室打造，移动端高性能、轻量级推断框架，同时拥有跨平台、高性能、模型压缩、代码裁剪等众多突出优势。TNN框架在原有Rapidnet、ncnn框架的基础上进一步加强了移动端设备的支持以及性能优化，同时也借鉴了业界主流开源框架高性能和良好拓展性的优点。目前TNN已经在手Q、微视、P图等应用中落地，欢迎大家参与协同共建，促进TNN推断框架进一步完善。

tonet

The official implementation of "TONet: Tone-Octave Network for Singing Melody Extraction from Polyphonic Music"

torchcrepe

Pytorch implementation of the CREPE pitch tracker

tracking-by-detection

Multiple object tracking (MOT) algorithm implemented in C++

traditional-speech-enhancement

Spectral Subtraction, Wiener Filtering, MMSE

tsegan

The implement of the paper 'Time-domain Speech Enhancement with GenerativeAdversarial Learning'

tspnn

Two-stage progressive neural network for acoustic echo cancellation

tts-tutorial

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.

unified2021

A UNIFIED SPEECH ENHANCEMENT FRONT-END FOR ONLINE DEREVERBERATION, ACOUSTIC ECHO CANCELLATION, AND SOURCE SEPARATION