EspnetEnd-to-End Speech Processing Toolkit
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…
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.
EaBNetThis is the repo of the manuscript "Embedding and Beamforming: All-Neural Causal Beamformer for Multichannel Speech Enhancement", which was submitted to ICASSP2022.
semetricsSpeech Enhancement Metrics (PESQ, CSIG, CBAK, COVL)
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.
fdndlpA speech dereverberation algorithm, also called wpe
SpleeterRTReal time monaural source separation base on fully convolutional neural network operates on Time-frequency domain.
deepbeamDeep learning based Speech Beamforming
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…