ePrints

Low-Power Audio Keyword Spotting Using Tsetlin Machines

Lookup NU author(s): Jie lei, Professor Rishad Shafik, Adrian WheeldonORCiD, Professor Alex Yakovlev

Downloads

• Published version [.pdf]

Licence

This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).

Abstract

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

Publication metadata

Author(s): Lei J, Rahman T, Shafik R, Wheeldon A, Yakovlev A, Granmo O-C, Kawsar F, Mathur A

Publication type: Article

Publication status: Published

Journal: Journal of Low Power Electronics and Applications

Year: 2021

Volume: 11

Issue: 2

Print publication date: 09/04/2021

Online publication date: 09/04/2021

Acceptance date: 07/04/2021

Date deposited: 24/06/2021

ISSN (electronic): 2079-9268

Publisher: MDPI AG

URL: https://doi.org/10.3390/jlpea11020018

DOI: 10.3390/jlpea11020018

Altmetrics

Funding

Share