Low-Power Audio Keyword Spotting using Tsetlin Machines

The emergence of Artificial Intelligence (AI) driven Keyword Spotting (KWS) technologies has revolutionized human to machine interaction. Yet, the challenge of end-to-end energy efficiency, memory footprint and system complexity of current Neural Network (NN) powered AI-KWS pipelines has remained ev...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-01
Main Authors: Lei, Jie, Rahman, Tousif, Shafik, Rishad, Wheeldon, Adrian, Yakovlev, Alex, Ole-Christoffer Granmo, Fahim Kawsar, Mathur, Akhil
Format: Article
Language:English
Subjects:
Algorithms
Artificial intelligence
Complexity
Energy conversion efficiency
Keywords
Machine learning
Neural networks
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The emergence of Artificial Intelligence (AI) driven Keyword Spotting (KWS) technologies has revolutionized human to machine interaction. Yet, the challenge of end-to-end energy efficiency, memory footprint and system complexity of current Neural Network (NN) powered AI-KWS pipelines has remained ever present. This paper evaluates KWS utilizing a learning automata powered machine learning algorithm called the Tsetlin Machine (TM). Through significant reduction in parameter requirements and choosing logic over arithmetic based processing, the TM offers new opportunities for low-power KWS while maintaining high learning efficacy. In this paper we explore a TM based keyword spotting (KWS) pipeline to demonstrate low complexity with faster rate of convergence compared to NNs. Further, we investigate the scalability with increasing keywords and explore the potential for enabling low-power on-chip KWS.
ISSN:2331-8422