{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:39:01Z","timestamp":1783183141875,"version":"3.54.6"},"reference-count":262,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Demant Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2021.3139508","type":"journal-article","created":{"date-parts":[[2021,12,30]],"date-time":"2021-12-30T20:49:45Z","timestamp":1640897385000},"page":"4169-4199","source":"Crossref","is-referenced-by-count":114,"title":["Deep Spoken Keyword Spotting: An Overview"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8634-7897","authenticated-orcid":false,"given":"Ivan","family":"Lopez-Espejo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6856-8928","authenticated-orcid":false,"given":"Zheng-Hua","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1382-9929","authenticated-orcid":false,"given":"John H. L.","family":"Hansen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jesper","family":"Jensen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/02763869.2018.1404391"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268946"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854211"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-753"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319341"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2007-174"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707766"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706631"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1777"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-204"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178970"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IALP48816.2019.9037714"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-480"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134087"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178863"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1676"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2936282"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266505"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115555"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1991.150338"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-397"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854370"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2015.121"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1485"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1054010"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683479"},{"key":"ref27","article-title":"Suspending noise cancellation using keyword spotting","author":"Scott","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-352"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846306"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462688"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683557"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1003"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.26438\/ijcse\/v7i1.757769"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-019-09739-y"},{"key":"ref35","volume-title":"Speech Databases: Features, Techniques and Evaluation Measures","author":"Mary","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-013-9217-1"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2017.7510508"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/sym11081018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053009"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-817"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/BIOCAS.2018.8584832"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682534"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-020-00176-2"},{"key":"ref44","article-title":"Robust speech recognition on intelligent mobile devices with dual-microphone","author":"L\u00f3pez-Espejo","year":"2017"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003745"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74695-9_23"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/DSD.2019.00053"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2891838"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004005"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1363"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1045"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3177"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1230"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.06.005"},{"key":"ref55","first-page":"1","article-title":"DONUT: CTC-based query-by-example keyword spotting","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Lugosch"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003781"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2185"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1979"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2763"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268974"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICICSP48821.2019.8958609"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053191"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref64","first-page":"1","article-title":"Sequence transduction with recurrent neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Graves"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-45528-0"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2018.8631574"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003738"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1877"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053395"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054039"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1412"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-76153-9_28"},{"key":"ref74","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref75","article-title":"Hello edge: Keyword spotting on microcontrollers","author":"Zhang","year":"2018","journal-title":"arXiv:1711.07128v3"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1759"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2019.8885980"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683474"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1992"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1121\/1.1915893"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287772"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_3"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.08.006"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764268"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461624"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ISC246665.2019.9071684"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1049\/iet-spr.2019.0027"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2568"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1286"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-136"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64680-0"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1737"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682682"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1916"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1521"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054538"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054618"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1761"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-383"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414339"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2016.7918366"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1846"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414156"},{"issue":"4","key":"ref105","first-page":"35","article-title":"Modern information retrieval: A brief overview","volume":"24","author":"Singhal","year":"2001","journal-title":"IEEE Comput. Soc. Tech. Committee Data Eng."},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5373341"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707765"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2019.00127"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CyberC.2019.00082"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462575"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462165"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1250\/ast.20.397"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-1"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953204"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2414"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1436"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ICCP48234.2019.8959645"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-351"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2726060"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1393"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462346"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1580"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1262"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3132"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref127","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kipf"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2010"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2984089"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3092567"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref132","first-page":"125","article-title":"WaveNet: A generative model for raw audio","volume-title":"Proc. ISCA Speech Synthesis Workshop","author":"van den Oord"},{"key":"ref133","article-title":"A neural attention model for speech command recognition","author":"de Andrade","year":"2018","journal-title":"arXiv:1808.08929"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-458"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00154"},{"key":"ref136","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861v1"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-383"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2016.7918460"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683669"},{"key":"ref141","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sutskever"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-82"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413588"},{"key":"ref144","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2613"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414848"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15825-4_10"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729392"},{"key":"ref150","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1335"},{"key":"ref152","first-page":"3661","article-title":"Robust keyword spotting via recycle-pooling for mobile game","volume-title":"Proc. Annu. Conf. Int. Speech Commun. Assoc.","author":"An"},{"key":"ref153","volume-title":"Launching the Speech Commands Dataset","author":"Warden","year":"2017"},{"key":"ref154","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018","journal-title":"arXiv:1804.03209"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_8507"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953242"},{"key":"ref157","article-title":"A monaural speech enhancement method for robust small-footprint keyword spotting","author":"Gu","year":"2019","journal-title":"arXiv:1906.08415"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682460"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1420"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1145\/3178115"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413740"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3006"},{"key":"ref163","volume-title":"Google Nest and Home device specifications","year":"2022"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5496202"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.02.004"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-30441-0_35"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1262"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472778"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1186"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-72"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-27947-9_21"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref173","first-page":"1","article-title":"Intriguing properties of neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Szegedy"},{"key":"ref174","first-page":"1","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Goodfellow"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053193"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413448"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1644"},{"key":"ref178","first-page":"1857","article-title":"Improved deep metric learning with multi-class N-pair loss objective","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383571"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-571"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2678164"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1121\/1.426686"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1145\/1998384.1998386"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16226-3_7"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-73819-2_12"},{"key":"ref187","volume-title":"Hey Siri: An On-device DNN-powered Voice Trigger for Apple\u2019s Personal Assistant","author":"Team","year":"2017"},{"key":"ref188","volume-title":"Number of Digital Voice Assistants in Use Worldwide From 2019 to 2024","year":"2020"},{"key":"ref189","volume-title":"Keyword Recognition","year":"2021"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1428"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162830"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1121\/1.400476"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1984.1172716"},{"key":"ref195","article-title":"DARPA TIMIT acoustic phonetic continuous speech corpus CDROM","author":"Garofolo","year":"4930"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-313"},{"key":"ref197","first-page":"1","article-title":"The design for the wall street journal-based CSR corpus","volume-title":"Proc. Speech Natural Lang.","author":"Paul"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683546"},{"key":"ref199","article-title":"AISHELL-2: Transforming Mandarin ASR research into industrial scale","author":"Du","year":"2018","journal-title":"arXiv:1808.10583"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004014"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053313"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1204"},{"key":"ref203","volume-title":"FaNT-Filtering and Noise Adding Tool","author":"Hirsch","year":"2015"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref206","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015","journal-title":"arXiv:1510.08484"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.10.005"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref211","volume-title":"Creative Commons Attribution 4.0 International","year":"2022"},{"key":"ref212","volume-title":"Machine Learning Crash Course\u2014Classification: Accuracy","year":"2022"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-6-96"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-25465-X_40"},{"issue":"2","key":"ref215","doi-asserted-by":"crossref","first-page":"1","DOI":"10.5121\/ijdkp.2015.5201","article-title":"A review on evaluation metrics for data classification evaluations","volume":"5","author":"Hossin","year":"2015","journal-title":"Int. J. Data Mining Knowl. Manage. Process."},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.1036"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-69384-0_45"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2005.10.010"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.02.003"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1665"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054221"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2006.887018"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462166"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1997-504"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.3390\/s18072060"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74200-5_19"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.03.001"},{"key":"ref228","article-title":"Speaker recognition based on deep learning: An overview","author":"Bai","year":"2020","journal-title":"arXiv:2012.00931"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915322"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2019.2899067"},{"key":"ref231","volume-title":"OpenKWS13 Keyword Search Evaluation Plan","year":"2013"},{"key":"ref232","first-page":"61","article-title":"Howl: A deployed, open-source wake word detection system","volume-title":"Proc. 2nd Workshop NLP Open Source Softw. (NLP-OSS)","author":"Tang"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-316"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-726"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-691"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472833"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472837"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-601"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143874"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0118432"},{"key":"ref241","volume-title":"Information Retrieval","author":"van Rijsbergen","year":"1979"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.1109\/ICSP.2018.8652301"},{"key":"ref243","first-page":"1","article-title":"Neural architecture search with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zoph"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref245","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2950602"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683733"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054127"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2520091"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451096"},{"key":"ref252","first-page":"1","article-title":"Seeing wake words: Audio-visual keyword spotting","volume-title":"Proc. Brit. Mach. Vis. Virtual Conf.","author":"Momeni"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.5772\/6364"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref256","article-title":"LRS3-TED: A large-scale dataset for visual speech recognition","author":"Afouras","year":"2018","journal-title":"arXiv:1809.00496"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053954"},{"key":"ref258","first-page":"1","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hinton"},{"key":"ref259","article-title":"An overview of deep semi-supervised learning","author":"Ouali","year":"2020","journal-title":"arXiv:2006.05278"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054760"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-602"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2017.12.011"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09665775.pdf?arnumber=9665775","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T22:01:44Z","timestamp":1705183304000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9665775\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":262,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3139508","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}