activity
20172021
most citedVisualizing Deep Neural Networks for Speech Recognition with Learned Topographic Filter Maps

4 citations · 8 across the 4 of their papers we have counts for

collaborators

6 papers

cs.CV20214 cited

Evaluation of deep lift pose models for 3D rodent pose estimation based on geometrically triangulated data

Indrani Sarkar, Indranil Maji, Charitha Omprakash +3

The assessment of laboratory animal behavior is of central interest in modern neuroscience research. Behavior is typically studied in terms of pose changes, which are ideally captu…

eess.IV2021

Uncertainty-Aware Temporal Self-Learning (UATS): Semi-Supervised Learning for Segmentation of Prostate Zones and Beyond

Anneke Meyer, Suhita Ghosh, Daniel Schindele +4

Various convolutional neural network (CNN) based concepts have been introduced for the prostate's automatic segmentation and its coarse subdivision into transition zone (TZ) and pe…

cs.LG2020

Gradient-Adjusted Neuron Activation Profiles for Comprehensive Introspection of Convolutional Speech Recognition Models

Andreas Krug, Sebastian Stober

Deep Learning based Automatic Speech Recognition (ASR) models are very successful, but hard to interpret. To gain better understanding of how Artificial Neural Networks (ANNs) acco…

eess.AS20194 cited

Visualizing Deep Neural Networks for Speech Recognition with Learned Topographic Filter Maps

Andreas Krug, Sebastian Stober

The uninformative ordering of artificial neurons in Deep Neural Networks complicates visualizing activations in deeper layers. This is one reason why the internal structure of such…

cs.AI2018

Hybrid Active Inference

André Ofner, Sebastian Stober

We describe a framework of hybrid cognition by formulating a hybrid cognitive agent that performs hierarchical active inference across a human and a machine part. We suggest that,…

cs.LG2017

Transfer Learning for Speech Recognition on a Budget

Julius Kunze, Louis Kirsch, Ilia Kurenkov +3

End-to-end training of automated speech recognition (ASR) systems requires massive data and compute resources. We explore transfer learning based on model adaptation as an approach…