11 results found Sort:

resemble-ai
resemble-enhance resemble-ai
164
1.5k
mit
19
AI powered speech denoising and enhancement
denoise speech-denoising speech-processing speech-enhancement
Created 2023-11-15
13 commits to main branch, last one 18 days ago
drethage
speech-denoising-wavenet drethage
164
680
mit
19
A neural network for end-to-end speech denoising
speech wavenet end-to-end deep-learning neural-networks machine-learning speech-denoising speech-processing
Created 2017-06-19
3 commits to master branch, last one 7 years ago
breizhn
DTLN breizhn
161
595
mit
9
Tensorflow 2.x implementation of the DTLN real time speech denoising model. With TF-lite, ONNX and real-time audio processing support.
onnx audio keras tf-lite dtln-model tensorflow raspberry-pi deep-learning dns-challenge noise-reduction real-time-audio audio-processing speech-denoising noise-suppression speech-processing speech-enhancement
Created 2020-05-11
101 commits to master branch, last one 2 years ago
posenhuang
deeplearningsourceseparation posenhuang
135
366
other
33
Deep Recurrent Neural Networks for Source Separation
rnn matlab deep-learning audio-separation speech-denoising source-separation speech-separation
Created 2014-07-20
88 commits to master branch, last one 3 years ago
NVIDIA
CleanUNet NVIDIA
51
303
mit
11
Official PyTorch Implementation of CleanUNet (ICASSP 2022)
noise-reduction speech-denoising speech-processing speech-enchacement
Created 2022-07-05
7 commits to main branch, last one 2 years ago
madhavmk
Noise2Noise-audio_denoising_without_clean_training_data madhavmk
42
180
mit
7
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...
speech autoencoder noise2noise deep-learning noise-removal audio-denoising data-collection noise-reduction speech-denoising audio-enhancement speech-enhancement
Created 2021-03-28
19 commits to main branch, last one 3 years ago
skirdey
voicerestore skirdey
9
91
mit
7
VoiceRestore: Flow-Matching Transformers for Universal Speech Restoration
voicefixer transformers speech-denoising speech-enhancement speech-restoration audio-super-resolution conditional-flow-matching
Created 2024-09-06
49 commits to main branch, last one 2 months ago
haoxiangsnr
spiking-fullsubnet haoxiangsnr
14
79
mit
4
Official repository of Spiking-FullSubNet, the Intel N-DNS Challenge Algorithmic Track Winner.
noise-reduction speech-denoising speech-enhancement neuromorphic-computing neuromorphic-audio-processing
Created 2023-04-25
280 commits to main branch, last one 9 months ago
liqingchunnnn
Only-Noisy-Training liqingchunnnn
15
64
unknown
2
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.
pytorch speech-denoising self-supervised-learning
Created 2022-01-30
39 commits to main branch, last one about a year ago
AmbiqAI
nnse AmbiqAI
6
35
bsd-3-clause
2
NNSE (Neural Network Speech Enhancement) is a speech-denoiser optimized to run on Ambiq's low power platform
ai ambiq tinyml modelzoo neuralspot ambiq-micro speech-denoising
Created 2023-02-08
53 commits to main branch, last one about a year ago
crlandsc
torch-log-wmse crlandsc
1
28
apache-2.0
2
logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source separation systems.
ai bss mss audio music torch python audio-quality deep-learning loss-functions audio-denoising audio-separation machine-learning sound-processing sound-separation speech-denoising audio-source-separation music-source-separation sound-source-separation audio-quality-assessment
Created 2024-03-28
74 commits to main branch, last one 4 months ago