semetricsSpeech Enhancement Metrics (PESQ, CSIG, CBAK, COVL)
Stars: ✭ 39 (+14.71%)
Mutual labels: speech-enhancement
Voice-Separation-and-EnhancementA framework for quick testing and comparing multi-channel speech enhancement and separation methods, such as DSB, MVDR, LCMV, GEVD beamforming and ICA, FastICA, IVA, AuxIVA, OverIVA, ILRMA, FastMNMF.
Stars: ✭ 60 (+76.47%)
Mutual labels: speech-enhancement
fdndlpA speech dereverberation algorithm, also called wpe
Stars: ✭ 115 (+238.24%)
Mutual labels: speech-enhancement
awesome-speech-enhancementA curated list of awesome Speech Enhancement papers, libraries, datasets, and other resources.
Stars: ✭ 48 (+41.18%)
Mutual labels: speech-enhancement
speech-enhancement-WGANspeech enhancement GAN on waveform/log-power-spectrum data using Improved WGAN
Stars: ✭ 35 (+2.94%)
Mutual labels: speech-enhancement
Speech Enhancement MMSE-STSAA statistical model-based Speech Enhancement Using MMSE-STSA
Stars: ✭ 54 (+58.82%)
Mutual labels: speech-enhancement
SpleeterRTReal time monaural source separation base on fully convolutional neural network operates on Time-frequency domain.
Stars: ✭ 111 (+226.47%)
Mutual labels: speech-enhancement
deepbeamDeep learning based Speech Beamforming
Stars: ✭ 58 (+70.59%)
Mutual labels: speech-enhancement
ConvolutionaNeuralNetworksToEnhanceCodedSpeechIn this work we propose two postprocessing approaches applying convolutional neural networks (CNNs) either in the time domain or the cepstral domain to enhance the coded speech without any modification of the codecs. The time domain approach follows an end-to-end fashion, while the cepstral domain approach uses analysis-synthesis with cepstral d…
Stars: ✭ 25 (-26.47%)
Mutual labels: speech-enhancement
torchsubbandPytorch implementation of subband decomposition
Stars: ✭ 63 (+85.29%)
Mutual labels: speech-enhancement
EspnetEnd-to-End Speech Processing Toolkit
Stars: ✭ 4,533 (+13232.35%)
Mutual labels: speech-enhancement
Noise2Noise-audio denoising without clean training dataSource 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…
Stars: ✭ 49 (+44.12%)
Mutual labels: speech-enhancement
Voice-Denoising-ANA Conditional Generative Adverserial Network (cGAN) was adapted for the task of source de-noising of noisy voice auditory images. The base architecture is adapted from Pix2Pix.
Stars: ✭ 42 (+23.53%)
Mutual labels: speech-enhancement
