GmiSa1990

TCN

Sequence modeling benchmarks and temporal convolutional networks

Fre-GAN-pytorch

Fre-GAN: Adversarial Frequency-consistent Audio Synthesis

hifi-gan

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

hifigan-denoiser

HiFi-GAN: High Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks

waveglow

A Flow-based Generative Network for Speech Synthesis

tacotron2

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

ganhacks

starter from "How to Train a GAN?" at NIPS2016

melgan-neurips

GAN-based Mel-Spectrogram Inversion Network for Text-to-Speech Synthesis

A-Convolutional-Recurrent-Neural-Network-for-Real-Time-Speech-Enhancement

A minimum unofficial implementation of the "A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement" (CRN) using PyTorch

ParallelWaveGAN

Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch

melgan

MelGAN vocoder (compatible with NVIDIA/tacotron2)

TTS

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Conv-TasNet

A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permutation Invariant Training (PIT).

bandwidth_extension

getopt-for-windows

getopt.h and getopt.c are very often used in linux, to make it easy for windows user, two files were extracted from glibc

tfnet

aecnn-rpi

Real-time Python framework for DNN-based speech enhancement

se_relativisticgan

Keras framework for speech enhancement using relativistic GANs

MNN

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

aubio

a library for audio and music analysis

lyra

A Very Low-Bitrate Codec for Speech Compression

DCASE2020_task1

Code for DCASE 2020 task 1a and task 1b.

DCASE2019-Task1

Code for DCASE 2019 Task 1a, 1b and 1c

DeepComplexCRN

seriesnet

Time series prediction using dilated causal convolutional neural nets (temporal CNN)

DeepXi

Deep Xi: A deep learning approach to a priori SNR estimation implemented in TensorFlow 2/Keras. For speech enhancement and robust ASR.

ios-cmake

A CMake toolchain file for iOS, macOS, watchOS & tvOS C/C++/Obj-C++ development

awesome-cpp

A curated list of awesome C++ (or C) frameworks, libraries, resources, and shiny things. Inspired by awesome-... stuff.

CPlusPlusThings

C++那些事

Real-Time-Voice-Cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time