cs.SDOct 28, 2025

TsetlinKWS: A 65nm 16.58uW, 0.63mm2 State-Driven Convolutional Tsetlin Machine-Based Accelerator For Keyword Spotting

Authors: Baizhou Lin, Yuetong Fang, Renjing Xu, Rishad Shafik, Jagmohan Chauhan

Organizations: University of Southampton, SO17 1BJ Southampton, U.K. · University College London, WC1E 6BT London, U.K.

Abstract

The Tsetlin Machine (TM) has recently attracted attention as a low-power alternative to neural networks due to its simple and interpretable inference mechanisms. However, its performance on speech-related tasks remains limited. This paper proposes TsetlinKWS, the first algorithm-hardware co-design framework for the Convolutional Tsetlin Machine (CTM) on the 12-keyword spotting task. Firstly, we introduce a novel Mel-Frequency Spectral Coefficient and Spectral Flux (MFSC-SF) feature extraction scheme together with spectral convolution, achieving a record-high accuracy of 87.35% for TM-based models on the 12-keyword spotting task. Secondly, we develop an Optimized Grouped Block-Compressed Sparse Row (OG-BCSR) algorithm that delivers a remarkable 9.84×\times reduction in model size, significantly improving the storage efficiency of CTMs. Finally, we propose a state-driven architecture tailored for CTMs, which simultaneously exploits data reuse and sparsity to attain high energy efficiency. The full system is evaluated in 65 nm process technology, consuming 16.58 μμW at 0.7 V with a compact 0.63 mm2^2 core area. TsetlinKWS demonstrates a Power-Performance-Area (PPA) product of 60.2 and requires only 907k logic operations per inference, corresponding to 1.4×\times and 10×\times reductions, respectively, compared with state-of-the-art KWS accelerators. These results position the CTM as a highly efficient candidate for ultra-low-power speech applications.

Figures & tables

Explore similar work

CardsList
  1. Sub-Model Short-Term Memory Convolutions for Keyword Spotting Systems on Device

    Sep 28, 2026Paweł Warlewski, Artur Czeczko, Artur Szumaczuk +2Keyword SpottingSpeech Processing

  2. A Multiplication-Free Feature Extractor for Signal Classification: Keyword Spotting Case Study

    Aug 17, 2026Radu Dogaru, Ioana DogaruSpeech ProcessingTiny ML