Pinned Repositories
aspp
ASPP: Binaural Speech Enhancement with Atomic Speech Presence Probability Estimation
audacity
Audio Editor
Audio-Denoising
A CNN for denoising speech.
Automatic-speech-sequence-segmentation
The Main Aim of this project is to segment and cluster an audio sample based on speaker when number of speakers are not known before hand. Main challenge in the process of speaker recognition is separting audio based on speaker.It can enhance the readability of an automatic speech transcription by structuring the audio stream into speaker turns and, when used together with speaker recognition systems, by providing the speaker's true identity.Other challenges are due to multiple speakers present at the time instant
BinWavenet
this project is coming from https://github.com/drethage/speech-denoising-wavenet, and i change some details, like speaker information and stack layer and so on. I also rewrite it with tensorflow.keras, it make me more comfortable.
ClearWave
Denoise Speech (Enhanced Speech or Speech enhancement) by Deep Learning (Using Keras and Tensorflow)
CNN-for-single-channel-speech-enhancement
Convolutional neural nets for single channel speech enhancement
setk
Tools for Speech Enhancement integrated with Kaldi
Speech-enhancement
In this project, we collected classic algorithms for speech enhancement. For those who need it. All data sets and algorithms are collected from the web and we do not own the copyright.
Studienarbeit
Studienarbeit: Noise Estimation based on EP in CIs
zk1001's Repositories
zk1001/Speech-enhancement
In this project, we collected classic algorithms for speech enhancement. For those who need it. All data sets and algorithms are collected from the web and we do not own the copyright.
zk1001/Studienarbeit
Studienarbeit: Noise Estimation based on EP in CIs
zk1001/aspp
ASPP: Binaural Speech Enhancement with Atomic Speech Presence Probability Estimation
zk1001/audacity
Audio Editor
zk1001/Audio-Denoising
A CNN for denoising speech.
zk1001/Automatic-speech-sequence-segmentation
The Main Aim of this project is to segment and cluster an audio sample based on speaker when number of speakers are not known before hand. Main challenge in the process of speaker recognition is separting audio based on speaker.It can enhance the readability of an automatic speech transcription by structuring the audio stream into speaker turns and, when used together with speaker recognition systems, by providing the speaker's true identity.Other challenges are due to multiple speakers present at the time instant
zk1001/BinWavenet
this project is coming from https://github.com/drethage/speech-denoising-wavenet, and i change some details, like speaker information and stack layer and so on. I also rewrite it with tensorflow.keras, it make me more comfortable.
zk1001/DeepXi
Deep Xi: A Deep Learning Approach to A Priori SNR Estimation. Used for Speech Enhancement and robust ASR.
zk1001/setk
Tools for Speech Enhancement integrated with Kaldi
zk1001/fullcalendar-docs
Static content for fullcalendar.io
zk1001/IntelligibilityEnhancement
Implementation of different speech intelligibility enhancement algorithms
zk1001/iOS-TwoExternalMics
Implementation of Adaptive Noise Reduction and Background Noise Classification using External Microphones on iOS
zk1001/Meta-Learning-Generalizing-Speech-Denoising
zk1001/MS2-Noise-Reduction
Implementing neural networks to reduce noise in MS2 spectra.
zk1001/Museum-of-Tomorrow-Robust-Speech-Recognition
Denoising scripts for use in the robust recognition project in the Museum of Tomorrow
zk1001/nara_wpe
Different implementations of "Weighted Prediction Error" for speech dereverberation
zk1001/noisereduce
Noise reduction / speech enhancement for python using spectral gating
zk1001/onssen
An open-source speech separation and enhancement library
zk1001/sednn
deep learning based speech enhancement using keras or pytorch, make it easy to use
zk1001/segan_pytorch
Speech Enhancement Generative Adversarial Network in PyTorch
zk1001/Speech-Denoise-With-Feature-Loss
本项目使用中文人声的数据集，在Speech Denoising with Deep Feature Losses网络的基础上fine-tune，得到对中文音频有更好去噪效果的结果
zk1001/Speech-Denoising
zk1001/Speech-enhancement-dsp
传统方法语音增强matlab实现 1、谱减法 2、维纳滤波法 3、卡尔曼滤波法
zk1001/speech-enhancement-WGAN
speech enhancement GAN on waveform/log-power-spectrum data using Improved WGAN
zk1001/speechdenoising-1
This repo has a Tensorflow implementation of speech denoising with an API service as well.
zk1001/Speechenhancement
语音增强算法：趁着中期，赶紧整理一版发上来，（多窗谱减、维纳、最优谱估计）
zk1001/Wave-U-Net-For-Speech-Enhancement
Improved speech enhancement with the Wave-U-Net, a deep convolutional neural network architecture for audio source separation, implemented for the task of speech enhancement in the time-domain.
zk1001/Wave-U-Net-for-Speech-Enhancement-1
Implement [Wave-U-Net](https://arxiv.org/abs/1806.03185) by PyTorch, and migrate it to the speech enhancement area.
zk1001/zk
zk1001/zk1001
Config files for my GitHub profile.