Search Results for author:
Found 4 papers, 1 papers with code
Gradient-Adjusted Neuron Activation Profiles for Comprehensive Introspection of Convolutional Speech Recognition Models
This includes different ways of visualizing features and clustering of GradNAPs to compare embeddings of different groups of inputs in any layer of a given network.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Visualizing Deep Neural Networks for Speech Recognition with Learned Topographic Filter Maps
The uninformative ordering of artificial neurons in Deep Neural Networks complicates visualizing activations in deeper layers.
Introspection for convolutional automatic speech recognition
Our method integrates information from many data examples through local introspection techniques for Convolutional Neural Networks (CNNs).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Transfer Learning for Speech Recognition on a Budget
End-to-end training of automated speech recognition (ASR) systems requires massive data and compute resources.
