Code for ITENE: Intrinsic Transfer Entropy Neural Estimator (arXiv version: https://arxiv.org/abs/1912.07277)
This python code estimates conditional mutual information (CMI) and mutual information (MI) for discrete and/or continuous variables using a nearest neighbors approach.
Non-linear digital self-interference cancellation for in-band full-duplex radios using neural networks
Detailed code used for researching machine learning for carrier frequency offset
Human presence detection using WiFi and Convolutional Neural Networks
C / MATLAB functions to evaluate mutual information for optical communications
Collections of Papers and Codes about Communication Systems Built by Autoencoder
Implementation of a neural network architecture to estimate channel log-likelihood ratios given a channel observation.
In 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 domain features. The proposed postprocessors in both domains are evaluated for various narrowband and wideband speech codecs in a wide range of conditions. The proposed postprocessor improves speech quality (PESQ) by up to 0.25 MOS-LQO points for G.711, 0.30 points for G.726, 0.82 points for G.722, and 0.26 points for adaptive multirate wideband codec (AMR-WB). In a subjective CCR listening test, the proposed postprocessor on G.711-coded speech exceeds the speech quality of an ITU-T-standardized postfilter by 0.36 CMOS points, and obtains a clear preference of 1.77 CMOS points compared to G.711, even en par with uncoded speech.
This repository contains the code for Characterizing the Decision Boundary of Deep Neural Networks
the python codes of paper "Communication-oriented Autoencoders - where Shannon meets Wiener"
