Gradient-adjusted Neuron Activation Profiles For Comprehensive Introspection Of Convolutional Speech Recognition Models

Abstract

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) accomplish their tasks, introspection methods have been proposed. Adapting such techniques from computer vision to speech recognition is not straight-forward, because speech data is more complex and less interpretable than image data. In this work, we introduce Gradient-adjusted Neuron Activation Profiles (GradNAPs) as means to interpret features and representations in Deep Neural Networks. GradNAPs are characteristic responses of ANNs to particular groups of inputs, which incorporate the relevance of neurons for prediction. We show how to utilize GradNAPs to gain insight about how data is processed in ANNs. 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. We demonstrate our proposed techniques usin

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykrug2020gradient

Related papers

• Visualizing Automatic Speech Recognition -- Means For A Better Understanding? (2022)4.52
• Analyzing Hidden Representations In End-to-end Automatic Speech Recognition Systems (2017)0.00
• Efficient Neural Architecture Search For End-to-end Speech Recognition Via Straight-through Gradients (2020)8.35
• Analyzing Analytical Methods: The Case Of Phonology In Neural Models Of Spoken Language (2020)6.77
• Towards Debugging Deep Neural Networks By Generating Speech Utterances (2019)0.00
• A Comparison Of Adaptation Techniques And Recurrent Neural Network Architectures (2018)3.58
• Light Gated Recurrent Units For Speech Recognition (2018)18.90
• Interpreting Intermediate Convolutional Layers Of Generative Cnns Trained On Waveforms (2021)5.84