11 results found Sort:

AI powered speech denoising and enhancement
Created 2023-11-15
10 commits to main branch, last one 4 months ago
A neural network for end-to-end speech denoising
Created 2017-06-19
3 commits to master branch, last one 7 years ago
160
581
mit
9
Tensorflow 2.x implementation of the DTLN real time speech denoising model. With TF-lite, ONNX and real-time audio processing support.
Created 2020-05-11
101 commits to master branch, last one 2 years ago
Deep Recurrent Neural Networks for Source Separation
Created 2014-07-20
88 commits to master branch, last one 3 years ago
51
293
mit
11
Official PyTorch Implementation of CleanUNet (ICASSP 2022)
Created 2022-07-05
7 commits to main branch, last one 2 years ago
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...
Created 2021-03-28
19 commits to main branch, last one 3 years ago
VoiceRestore: Flow-Matching Transformers for Universal Speech Restoration
Created 2024-09-06
49 commits to main branch, last one about a month ago
Official repository of Spiking-FullSubNet, the Intel N-DNS Challenge Algorithmic Track Winner.
Created 2023-04-25
280 commits to main branch, last one 8 months ago
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.
Created 2022-01-30
39 commits to main branch, last one about a year ago
5
29
bsd-3-clause
2
NNSE (Neural Network Speech Enhancement) is a speech-denoiser optimized to run on Ambiq's low power platform
Created 2023-02-08
53 commits to main branch, last one about a year ago
logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source separation systems.
Created 2024-03-28
74 commits to main branch, last one 3 months ago