910882575

AEC

AEC-Challenge

AEC Challenge

BSSD

Blind Source Separation and Dereverberation

cdr-dereverb

Coherence-based Dereverberation for Speech Enhancement

Complex-MTASSNet

Multi-Task Audio Source Separation, Two-Stage Model, Complex Domain.

denoiser

Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with skip-connections. It is optimized on both time and frequency domains, using multiple loss functions. Empirical evidence shows that it is capable of removing various kinds of background noise including stationary and non-stationary noises, as well as room reverb. Additionally, we suggest a set of data augmentation techniques applied directly on the raw waveform which further improve model performance and its generalization abilities.

DesktopSharing

桌面共享, 支持RTSP转发, RTSP推流, RTMP推流。

DFSMN-Based-Lightweight-Speech-Enhancement

Deep Feedforward sequential memory networks(FSMN)

directional-sparse-filtering-tf

Python Implementation for Directional Sparse Filtering with Tensorflow/Keras

eusipco2019

The code used for EUSIPCO 2019. The latest version is available in SoundSourceSeparation repository.

910882575/cdr-dereverb

Coherence-based Dereverberation for Speech Enhancement

910882575/BirdSoundsDenoising

910882575/Causal-U-Net

unofficial PyTorch implementation of 《A Causal U-net based Neural Beamforming Network for Real-Time Multi-Channel Speech Enhancement》

910882575/Amphion

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.

910882575/AQUA-Tk

AQUA-Tk = Audio QUality Assessment-Toolkit. (In development)

910882575/AudioLDM2

Text-to-Audio/Music Generation

910882575/Child-ASR-Paper

A list of papers for child ASR

910882575/DeepFilterNet

Noise supression using deep filtering

910882575/DSP-Digital-Audio-Processors-in-MATLAB

Digital audio processors such as a compressor/limiter, expander/gate, phase vocoder, multi-tap delay, flanger, reverb, dereverb, and others.

910882575/FilterBanks_FastPythonImplementation

Filter Banks, Fast Python Implementation

910882575/FreeVC

FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion

910882575/groove2groove

Code for "Groove2Groove: One-Shot Music Style Transfer with Supervision from Synthetic Data"

910882575/HierSpeechpp

The official implementation of HierSpeech++

910882575/LLVC

910882575/MNN

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

910882575/MNNKit

MNNKit is a collection of AI solutions for mobile developers, powered by MNN engine.

910882575/MultichannelAcousticEchoCancellation

910882575/odas

ODAS: Open embeddeD Audition System

910882575/rVAD

Matlab and Python libraries for an unsupervised method for robust voice activity detection (rVAD), as in the paper rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method.

910882575/SDrecord

910882575/so-vits-svc

SoftVC VITS Singing Voice Conversion

910882575/so-vits-svc-4.0-v2

SoftVC VITS Singing Voice Conversion

910882575/test

910882575/TinyNeuralNetwork

TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.

910882575/traditional-speech-enhancement

语音增强传统方法

910882575/Using-spectral-analysis-and-mapping-to-enhance-the-harmonicity-of-a-sound

Research MATLAB Project which analyses Inharmonic sounds, tries to find its most likely fundamental frequency and harmonic template, and performs spectral mapping to make it sound more harmonic while retaining most of its sound quality.

910882575/versatile_audio_super_resolution

Versatile audio super resolution (any -> 48kHz) with AudioSR.

910882575/visqol

Perceptual Quality Estimator for speech and audio

910882575/voicefixer

General Speech Restoration

910882575/voicefixer2

The second generation of VoiceFixer, a toolkit for general speech restoration. *Not affiliated with the original VoiceFixer repo*