Print Email Facebook Twitter A 23-μW Keyword Spotting IC With Ring-Oscillator-Based Time-Domain Feature Extraction Title A 23-μW Keyword Spotting IC With Ring-Oscillator-Based Time-Domain Feature Extraction Author Kim, Kwantae (Korea Advanced Institute of Science and Technology; University of Zürich) Gao, C. (TU Delft Electronics) Graca, Rui (University of Zürich) Kiselev, Ilya (University of Zürich) Yoo, Hoi Jun (Korea Advanced Institute of Science and Technology) Delbruck, Tobi (University of Zürich) Liu, Shih Chii (University of Zürich) Date 2022 Abstract This article presents the first keyword spotting (KWS) IC that uses a ring-oscillator-based time-domain processing technique for its analog feature extractor (FEx). Its extensive usage of time-encoding schemes allows the analog audio signal to be processed in a fully time-domain manner except for the voltage-to-time conversion stage of the analog front end. Benefiting from fundamental building blocks based on digital logic gates, it offers better technology scalability compared to conventional voltage-domain designs. Fabricated in a 65-nm CMOS process, the prototyped KWS IC occupies 2.03 mm 2 and dissipates 23- $\mu \text{W}$ power consumption, including analog FEx and digital neural network classifier. The 16-channel time-domain FEx achieves a 54.89-dB dynamic range for 16-ms frame shift size while consuming 9.3 $\mu \text{W}$. The measurement result verifies that the proposed IC performs a 12-class KWS task on the Google Speech Command dataset (GSCD) with >86% accuracy and 12.4-ms latency. Subject Analogbandpass filter (BPF)classifierfeature extractor (FEx)Google Speech Command dataset (GSCD)keyword spotting (KWS)rectifierrecurrent neural network (RNN)ring oscillatortime domain To reference this document use: http://resolver.tudelft.nl/uuid:a7f8ad3a-cf55-4350-a71b-6b605ca908bb DOI https://doi.org/10.1109/JSSC.2022.3195610 Embargo date 2023-07-01 ISSN 0018-9200 Source IEEE Journal of Solid State Circuits, 57 (11), 3298-3311 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 journal article Rights © 2022 Kwantae Kim, C. Gao, Rui Graca, Ilya Kiselev, Hoi Jun Yoo, Tobi Delbruck, Shih Chii Liu Files PDF A_23_W_Keyword_Spotting_I ... action.pdf 6.15 MB Close viewer /islandora/object/uuid:a7f8ad3a-cf55-4350-a71b-6b605ca908bb/datastream/OBJ/view