Print Email Facebook Twitter An Area-Efficient Ultra-Low-Power Time-Domain Feature Extractor for Edge Keyword Spotting Title An Area-Efficient Ultra-Low-Power Time-Domain Feature Extractor for Edge Keyword Spotting Author Chen, Qinyu (University of Zürich) Chang, Yaoxing (University of Zürich) Kim, Kwantae (University of Zürich) Gao, C. (TU Delft Electronics) Liu, Shih Chii (University of Zürich) Date 2023 Abstract Keyword spotting (KWS) is an important task on edge low-power audio devices. A typical edge KWS system consists of a front-end feature extractor which outputs mel-scale frequency cepstral coefficients (MFCC) features followed by a back-end neural network classifier. KWS edge designs aim for the best power-performance-area metrics. This work proposes an area-efficient ultra-low-power time-domain infinite impulse response (IIR) filter-based feature extractor for a KWS system. It uses a serial architecture, and the architecture is further optimized for a low-cost computing structure and mixed-precision bit selection of the IIR coefficients while maintaining good KWS accuracy. Using a 65 nm process technology and a back-end neural network classifier, this simulated feature extractor has an area of 0.02 mm2 and achieves 3.3 μW @ 1.2 V, and achieves 92.5% accuracy on a 10-keyword, 12-class KWS task using the GSCD dataset. Subject hardware accelerationinfinite impulse response (IIR)Keyword spotting (KWS)long short-term memory To reference this document use: http://resolver.tudelft.nl/uuid:580e5a49-5028-45fa-bcf6-0747836ecf40 DOI https://doi.org/10.1109/ISCAS46773.2023.10181602 Publisher Institute of Electrical and Electronics Engineers (IEEE) Embargo date 2024-01-22 ISBN 9781665451093 Source ISCAS 2023 - 56th IEEE International Symposium on Circuits and Systems, Proceedings Event 56th IEEE International Symposium on Circuits and Systems, ISCAS 2023, 2023-05-21 → 2023-05-25, Monterey, United States Series Proceedings - IEEE International Symposium on Circuits and Systems, 0271-4310, 2023-May Bibliographical note Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type conference paper Rights © 2023 Qinyu Chen, Yaoxing Chang, Kwantae Kim, C. Gao, Shih Chii Liu Files PDF An_Area_Efficient_Ultra_L ... otting.pdf 1.36 MB Close viewer /islandora/object/uuid:580e5a49-5028-45fa-bcf6-0747836ecf40/datastream/OBJ/view