Low-Power Audio Keyword Spotting using Tsetlin Machines
This addresses the problem of low-power, on-chip keyword spotting for human-machine interaction, though it appears incremental as it applies an existing method to a new domain.
The paper tackled the challenge of energy efficiency and complexity in AI-driven keyword spotting by evaluating Tsetlin Machines, achieving faster convergence and reduced parameters compared to neural networks while maintaining high learning efficacy.
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.