Low-Power Audio Keyword Spotting using Tsetlin Machines

by   Jie Lei, et al.

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.


page 9

page 16


Ultra-Low Power Keyword Spotting at the Edge

Keyword spotting (KWS) has become an indispensable part of many intellig...

Ultra-low power on-chip learning of speech commands with phase-change memories

Embedding artificial intelligence at the edge (edge-AI) is an elegant so...

Small-Footprint Keyword Spotting on Raw Audio Data with Sinc-Convolutions

Keyword Spotting (KWS) enables speech-based user interaction on smart de...

The Why, What and How of Artificial General Intelligence Chip Development

The AI chips increasingly focus on implementing neural computing at low ...

A 14uJ/Decision Keyword Spotting Accelerator with In-SRAM-Computing and On Chip Learning for Customization

Keyword spotting has gained popularity as a natural way to interact with...

Neural Network Design for Energy-Autonomous AI Applications using Temporal Encoding

Neural Networks (NNs) are steering a new generation of artificial intell...

Low-Power Low-Latency Keyword Spotting and Adaptive Control with a SpiNNaker 2 Prototype and Comparison with Loihi

We implemented two neural network based benchmark tasks on a prototype c...