Explaining the Attention Mechanism of End-to-End Speech Recognition Using Decision Trees

The attention mechanism has largely improved the performance of end-to-end speech recognition systems. However, the underlying behaviours of attention is not yet clearer. In this study, we use decision trees to explain how the attention mechanism impact itself in speech recognition. The results indi...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Wang, Yuanchao, Du, Wenji, Cai, Chenghao, Xu, Yanyan
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 08.10.2021
Subjects
Coders
Decision trees
Speech recognition
Voice recognition
Online AccessGet full text

Cover

More Information
Summary:The attention mechanism has largely improved the performance of end-to-end speech recognition systems. However, the underlying behaviours of attention is not yet clearer. In this study, we use decision trees to explain how the attention mechanism impact itself in speech recognition. The results indicate that attention levels are largely impacted by their previous states rather than the encoder and decoder patterns. Additionally, the default attention mechanism seems to put more weights on closer states, but behaves poorly on modelling long-term dependencies of attention states.
ISSN:2331-8422