{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T17:20:31Z","timestamp":1763400031664,"version":"3.41.0"},"reference-count":68,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T00:00:00Z","timestamp":1634515200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"EU ERC","award":["715037"],"award-info":[{"award-number":["715037"]}]},{"name":"Scientific Research Flanders"},{"DOI":"10.13039\/501100011878","name":"Flemish Government","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100011878","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2021,11,30]]},"abstract":"<jats:p>In recent years, Keyword Spotting (KWS) has become a crucial human\u2013machine interface for mobile devices, allowing users to interact more naturally with their gadgets by leveraging their own voice. Due to privacy, latency and energy requirements, the execution of KWS tasks on the embedded device itself instead of in the cloud, has attracted significant attention from the research community. However, the constraints associated with embedded systems, including limited energy, memory, and computational capacity, represent a real challenge for the embedded deployment of such interfaces. In this article, we explore and guide the reader through the design of KWS systems. To support this overview, we extensively survey the different approaches taken by the recent state-of-the-art (SotA) at the algorithmic, architectural, and circuit level to enable KWS tasks in edge, devices. A quantitative and qualitative comparison between relevant SotA hardware platforms is carried out, highlighting the current design trends, as well as pointing out future research directions in the development of this technology.<\/jats:p>","DOI":"10.1145\/3474365","type":"journal-article","created":{"date-parts":[[2021,10,19]],"date-time":"2021-10-19T01:02:15Z","timestamp":1634605335000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Hardware Acceleration for Embedded Keyword Spotting: Tutorial and Survey"],"prefix":"10.1145","volume":"20","author":[{"given":"J. S. P.","family":"Giraldo","sequence":"first","affiliation":[{"name":"ESAT-MICAS KU Leuven, Leuven, Belgium"}]},{"given":"Marian","family":"Verhelst","sequence":"additional","affiliation":[{"name":"ESAT-MICAS KU Leuven, Leuven, Belgium"}]}],"member":"320","published-online":{"date-parts":[[2021,10,18]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/2699343.2699349"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462688"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472820"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/AINA.2010.187"},{"key":"e_1_3_1_6_2","article-title":"Hello edge: Keyword spotting on microcontrollers","author":"Zhang Yundong","year":"2017","unstructured":"Yundong Zhang, Naveen Suda, Liangzhen Lai, and Vikas Chandra. 2017. Hello edge: Keyword spotting on microcontrollers. arXiv:1711.07128. Retrieved from https:\/\/arxiv.org\/abs\/1711.07128.","journal-title":"arXiv:1711.07128."},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3212725.3212731"},{"key":"e_1_3_1_8_2","article-title":"Hardware aware training for efficient keyword spotting on general purpose and specialized hardware","author":"Blouw Peter","year":"2020","unstructured":"Peter Blouw, Gurshaant Malik, Benjamin Morcos, Aaron R. Voelker, and Chris Eliasmith. 2020. Hardware aware training for efficient keyword spotting on general purpose and specialized hardware. arXiv:2009.04465. Retrieved from https:\/\/arxiv.org\/abs\/2009.04465.","journal-title":"arXiv:2009.04465."},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1562"},{"key":"e_1_3_1_10_2","first-page":"166","volume-title":"Proceedings of the IEEE 44th European Solid State Circuits Conference","author":"Giraldo Juan Sebastian P.","year":"2018","unstructured":"Juan Sebastian P. Giraldo and Marian Verhelst. 2018. Laika: A 5 uW programmable LSTM accelerator for always-on keyword spotting in 65 nm CMOS. In Proceedings of the IEEE 44th European Solid State Circuits Conference. IEEE, 166\u2013169."},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3407001"},{"key":"e_1_3_1_12_2","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden Pete","year":"2018","unstructured":"Pete Warden. 2018. Speech commands: A dataset for limited-vocabulary speech recognition. arXiv:1804.03209. Retrieved from https:\/\/arxiv.org\/abs\/1804.03209.","journal-title":"arXiv:1804.03209."},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC19947.2020.9063000"},{"key":"e_1_3_1_14_2","article-title":"Tidigits Speech Corpus","author":"Leonard R. Gary","year":"1993","unstructured":"R. Gary Leonard and George Doddington. 1993. Tidigits Speech Corpus. Texas Instruments, Inc .","journal-title":"Texas Instruments, Inc"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2020.2968800"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2017.7870352"},{"key":"e_1_3_1_17_2","first-page":"139","volume-title":"Proceedings of the 2018 IEEE Symposium on VLSI Circuits","author":"Yin Shouyi","year":"2018","unstructured":"Shouyi Yin, Peng Ouyang, Shixuan Zheng, Dandan Song, Xiudong Li, Leibo Liu, and Shaojun Wei. 2018. A 141 uw, 2.46 pj\/neuron binarized convolutional neural network based self-learning speech recognition processor in 28 nm CMOS. In Proceedings of the 2018 IEEE Symposium on VLSI Circuits. IEEE, 139\u2013140."},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683474"},{"key":"e_1_3_1_19_2","article-title":"Always-on, Sub-300-nW, event-driven spiking neural network based on spike-driven clock-generation and clock-and power-gating for an ultra-low-power intelligent device","author":"Wang Dewei","year":"2020","unstructured":"Dewei Wang, Pavan Kumar Chundi, Sung Justin Kim, Minhao Yang, Joao Pedro Cerqueira, Joonsung Kang, Seunchul Jung, Sangjoon Kim, and Mingoo Seok. 2020. Always-on, Sub-300-nW, event-driven spiking neural network based on spike-driven clock-generation and clock-and power-gating for an ultra-low-power intelligent device. arXiv:2006.12314. Retrieved from https:\/\/arxiv.org\/abs\/2006.12314.","journal-title":"arXiv:2006.12314."},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.23919\/VLSIC.2019.8778028"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICICM48536.2019.8977176"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CICC48029.2020.9075923"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2924340"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2020.2997913"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.3012320"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2960948"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/A-SSCC47793.2019.9056941"},{"key":"e_1_3_1_28_2","article-title":"RNNAccel: A fusion recurrent neural network accelerator for edge intelligence","author":"Kao Chao-Yang","year":"2020","unstructured":"Chao-Yang Kao, Huang-Chih Kuo, Jian-Wen Chen, Chiung-Liang Lin, Pin-Han Chen, and Youn-Long Lin. 2020. RNNAccel: A fusion recurrent neural network accelerator for edge intelligence. arXiv:2010.13311. Retrieved from https:\/\/arxiv.org\/abs\/2010.13311.","journal-title":"arXiv:2010.13311."},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1988.196669"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/SiPS.2015.7345026"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004014"},{"key":"e_1_3_1_32_2","unstructured":"Knowles. 2005. Passive Microphone BJ-21590-000. Retrieved on April 29 2021 from https:\/\/www.digikey.be\/htmldatasheets\/production\/388648\/0\/0\/1\/bj-21590-000-drawing.html."},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.4324\/9780080473468"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0010-9452(75)80027-X"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2017.2752838"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268943"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053395"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3232195.3232219"},{"key":"e_1_3_1_39_2","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1109\/VLSIC.2018.8502343","volume-title":"Proceedings of the 2018 IEEE Symposium on VLSI Circuits","author":"Badami Komail","year":"2018","unstructured":"Komail Badami, Kushal Dakshina Murthy, Pieter Harpe, and Marian Verhelst. 2018. A 0.6 V 54DB SNR analog frontend with 0.18 THD for low power sensory applications in 65NM CMOS. In Proceedings of the 2018 IEEE Symposium on VLSI Circuits. IEEE, 241\u2013242."},{"key":"e_1_3_1_40_2","first-page":"97","volume-title":"Proceedings of the Institute of Phonetic Sciences","volume":"17","author":"Boersma Paul","year":"1993","unstructured":"Paul Boersma. 1993. Accurate short-term analysis of the fundamental frequency and the harmonics-to-noise ratio of a sampled sound. In Proceedings of the Institute of Phonetic Sciences. Vol. 17, Amsterdam, 97\u2013110."},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE-Berlin.2018.8576243"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2017.7870355"},{"issue":"1","key":"e_1_3_1_44_2","first-page":"291","article-title":"A 90 nm CMOS, 6 uW power-proportional acoustic sensing frontend for voice activity detection","volume":"51","author":"Badami Komail M. H.","year":"2015","unstructured":"Komail M. H. Badami, Steven Lauwereins, Wannes Meert, and Marian Verhelst. 2015. A 90 nm CMOS, 6 uW power-proportional acoustic sensing frontend for voice activity detection. IEEE Journal of Solid-State Circuits 51, 1 (2015), 291\u2013302.","journal-title":"IEEE Journal of Solid-State Circuits"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115555"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078631"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854370"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-352"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.5555\/1778066.1778092"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"issue":"5","key":"e_1_3_1_51_2","first-page":"73","article-title":"Neuromorphic silicon neuron circuits","volume":"31","author":"Indiveri Giacomo","year":"2011","unstructured":"Giacomo Indiveri, Bernab\u00e9 Linares-Barranco, Tara Julia Hamilton, Andr\u00e9 Van Schaik, Ralph Etienne-Cummings, Tobi Delbruck, Shih-Chii Liu, Piotr Dudek, Philipp H\u00e4fliger, Sylvie Renaud, Johannes Schemmel, Gert Cauwenberghs, John Arthur, Kai Hynna, Fopefolu Folowosele, Sylvain Sa\u00efghi, Teresa Serrano-Gotarredona, Jayawan Wijekoon, Yingxue Wang, and Kwabena Boahen. 2011. Neuromorphic silicon neuron circuits. Frontiers in Neuroscience 31, 5 (2011), 73.","journal-title":"Frontiers in Neuroscience"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2011.2182009"},{"issue":"6","key":"e_1_3_1_54_2","article-title":"Hey Siri: An on-device DNN-powered voice trigger for Apple\u2019s personal assistant","volume":"1","author":"Team Siri","year":"2017","unstructured":"Siri Team. 2017. Hey Siri: An on-device DNN-powered voice trigger for Apple\u2019s personal assistant. Apple Machine Learning Journal 1, 6 (2017).","journal-title":"Apple Machine Learning Journal"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/AICCSA47632.2019.9035275"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.5555\/3130379.3130725"},{"key":"e_1_3_1_58_2","article-title":"WRPN: Wide reduced-precision networks","author":"Mishra Asit","year":"2017","unstructured":"Asit Mishra, Eriko Nurvitadhi, Jeffrey J. Cook, and Debbie Marr. 2017. WRPN: Wide reduced-precision networks. arXiv:1709.01134. Retrieved from https:\/\/arxiv.org\/abs\/1709.01134.","journal-title":"arXiv:1709.01134."},{"key":"e_1_3_1_59_2","article-title":"On the quantization of recurrent neural networks","author":"Li Jian","year":"2021","unstructured":"Jian Li and Raziel Alvarez. 2021. On the quantization of recurrent neural networks. arXiv:2101.05453. Retrieved from https:\/\/arxiv.org\/abs\/2101.05453.","journal-title":"arXiv:2101.05453."},{"key":"e_1_3_1_60_2","article-title":"What is the state of neural network pruning?","author":"Blalock Davis","year":"2020","unstructured":"Davis Blalock, Jose Javier Gonzalez Ortiz, Jonathan Frankle, and John Guttag. 2020. What is the state of neural network pruning?arXiv:2003.03033. Retrieved from https:\/\/arxiv.org\/abs\/2003.03033.","journal-title":"arXiv:2003.03033."},{"key":"e_1_3_1_61_2","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"Hu Hengyuan","year":"2016","unstructured":"Hengyuan Hu, Rui Peng, Yu-Wing Tai, and Chi-Keung Tang. 2016. Network trimming: A data-driven neuron pruning approach towards efficient deep architectures. arXiv:1607.03250. Retrieved from https:\/\/arxiv.org\/abs\/1607.03250.","journal-title":"arXiv:1607.03250."},{"key":"e_1_3_1_62_2","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"Han Song","year":"2015","unstructured":"Song Han, Huizi Mao, and William J. Dally. 2015. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv:1510.00149. Retrieved from https:\/\/arxiv.org\/abs\/1510.00149.","journal-title":"arXiv:1510.00149."},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"e_1_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/1283780.1283790"},{"key":"e_1_3_1_65_2","unstructured":"Syntiant. 2019. The Speed and Power Advantage of a Purpose-Built Neural Compute Engine. RetrievedJune 2019 from https:\/\/www.syntiant.com\/post\/keyword-spotting-power-comparison."},{"key":"e_1_3_1_66_2","unstructured":"Joan Figueras UPC Barcelona CLEAN Training Leader Spain Herman E. Maes IMEC Leuven Dominique Thomas and ST Microelectronics France. Controlling Leakage Power in Nanometer CMOS: Technology Meets Design. Retrieved on April 29 2021 from https:\/\/www.edacentrum.de\/controlling-leakage-power-nanometer-cmos-technology-meets-design."},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.5555\/519954"},{"key":"e_1_3_1_68_2","unstructured":"A. R. M. Peter Greenhalgh. 2011. Big. LITTLE Processing with ARM Cortex\u2122-A15 & Cortex-A7. Retrieved on April 29 2021 from https:\/\/www.eetimes.com\/big-little-processing-with-arm-cortex-a15-cortex-a7\/."},{"key":"e_1_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2019.8662540"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474365","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474365","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:26Z","timestamp":1750188626000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474365"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,18]]},"references-count":68,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2021,11,30]]}},"alternative-id":["10.1145\/3474365"],"URL":"https:\/\/doi.org\/10.1145\/3474365","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"type":"print","value":"1539-9087"},{"type":"electronic","value":"1558-3465"}],"subject":[],"published":{"date-parts":[[2021,10,18]]},"assertion":[{"value":"2021-01-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-10-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}