Institute for Communications Technology, Technische Universität Braunschweig's repositories
CIL_Segmentation
[ITSC 2020] Class-Incremental Learning for Semantic Segmentation Re-Using Neither Old Data Nor Old Labels
Components-Loss
Components loss for neural networks in mask-based speech enhancement
Perceptual-Weighting-Filter-Loss
A perceptual weighting filter loss for DNN training in speech enhancement
bibliography
Group bibliography
revt-domain-generalization
Re-Parameterized Vision Transformer (ReVT) for Domain-Generalized Semantic Segmentation
PerfPredRec
This repository serves for reproducing the results of the paper "Performance Prediction for Semantic Segmentation by a Self-Supervised Image Reconstruction Decoder"
Two-Stage-Speech-Enhancement
Supplementary material for the paper "Speech Enhancement by LSTM-Based Noise Suppression Followed by CNN-Based Speech Restoration" by Maximilian Strake, Bruno Defraene, Kristoff Fluyt, Wouter Tirry, and Tim Fingscheidt.
PerfPredRecV2
This repository serves for reproducing the results of the paper "Improvements to Image Reconstruction-Based Performance Prediction for Semantic Segmentation in Highly Automated Driving"
relaxedAttention
fairseq-code extension for relaxed attention
espresso
Espresso: A Fast End-to-End Neural Speech Recognition Toolkit
SuperResolutionMultiscaleTraining
Code for Super-Resolution Multiscale Training