4 citations · 4 across the 2 of their papers we have counts for
3 papers
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.AS2019★ 4 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.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…