Layer-Wise Relevance Propagation for Explainable Deep Learning Based Speech Recognition

We develop a framework for incorporating explanations in a deep learning based speech recognition model. The most cited criticism against deep learning based methods across domains is the non-interpretability of the model. This means that the model in itself provides very less or no insight into whi...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) pp. 168 - 174
Main Author Bharadhwaj, Homanga
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2018
Subjects
Bi-directional GRU
Bidirectional control
Computational modeling
Computer architecture
Explainable Deep Learning
Hidden Markov models
Layer-wise relevance propagation
Neurons
Speech recognition
Task analysis
Online AccessGet full text
DOI10.1109/ISSPIT.2018.8642691

Cover

More Information
Summary:We develop a framework for incorporating explanations in a deep learning based speech recognition model. The most cited criticism against deep learning based methods across domains is the non-interpretability of the model. This means that the model in itself provides very less or no insight into which features of the input are most responsible for the model`s predictions, Layer-wise relevance propagation is an emerging technique for explaining the predictions of deep neural networks. It has shown great success in computer vision applications, but to the best of our knowledge there has been no application of its use in a speech-recognition setup. In this paper, we develop a bi-directional GRU based speech recognition model in such a way that layer-wise relevance propagation can be suitably applied to explain the recognition task. We show through simulation results that the benefit of explainability does not compromise on the model accuracy of speech recognition.
DOI:10.1109/ISSPIT.2018.8642691