AI powered speech denoising and enhancement

A neural network for end-to-end speech denoising

Tensorflow 2.x implementation of the DTLN real time speech denoising model. With TF-lite, ONNX and real-time audio processing support.

Deep Recurrent Neural Networks for Source Separation

Official PyTorch Implementation of CleanUNet (ICASSP 2022)

Source code for the paper titled "Speech Denoising without Clean Training Data: a Noise2Noise Approach". Paper accepted at the INTERSPEECH 2021 conference. This paper tackles the problem of the heavy dependence of clean speech data required by deep learning based audio denoising methods by showing that it is possible to train deep speech denoisi…

VoiceRestore: Flow-Matching Transformers for Universal Speech Restoration

Official repository of Spiking-FullSubNet, the Intel N-DNS Challenge Algorithmic Track Winner.

A statistical model-based Speech Enhancement Using MMSE-STSA

A curated list of awesome Speech Enhancement papers, libraries, datasets, and other resources.

A self-supervised speech denoising strategy named Only-Noisy Training (ONT), which solves the speech denoising problem with only noisy audio signals in audio space for the first time.

NNSE (Neural Network Speech Enhancement) is a speech-denoiser optimized to run on Ambiq's low power platform

logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source separation systems.

Speech Denoising using RNNs in Tensorflow

Unofficial implementation of ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speech

Removing noise from speech using 1-D & 2-D Convolutional Neural Network (CNN)

An implementation of the paper MetricGAN (ICML 2019) in pytorch with some changes.

Time-Frequency Regularized Overlapping Group Shrinkage

Denoising speech audio using different types of CNN's combined with MFCC's.