{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T03:38:08Z","timestamp":1782877088664,"version":"3.54.5"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003052","name":"Ministry of Trade, Industry and Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003052","name":"Korea Institute for Advancement of Technology (KIAT) through the National Innovation Cluster Research and Development Program","doi-asserted-by":"publisher","award":["P0006704"],"award-info":[{"award-number":["P0006704"]}],"id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF) by the Korean Government through the Ministry of Science and ICT","doi-asserted-by":"publisher","award":["NRF-2018R1C1B5031408"],"award-info":[{"award-number":["NRF-2018R1C1B5031408"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002519","name":"Education and Research Promotion Program of Korea University of Technology and Education (KOREATECH), in 2021","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002519","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003665","name":"High Performance Computing (HPC) Support Project by the MSIT and the National IT Industry Promotion Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3078715","type":"journal-article","created":{"date-parts":[[2021,5,10]],"date-time":"2021-05-10T16:23:54Z","timestamp":1620663834000},"page":"80682-80691","source":"Crossref","is-referenced-by-count":46,"title":["Wav2KWS: Transfer Learning From Speech Representations for Keyword Spotting"],"prefix":"10.1109","volume":"9","author":[{"given":"Deokjin","family":"Seo","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Kumoh National Institute of Technology (KIT), Gumi, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9193-8998","authenticated-orcid":false,"given":"Heung-Seon","family":"Oh","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Korea University of Technology and Education (KOREATECH), Cheonan, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8871-1979","authenticated-orcid":false,"given":"Yuchul","family":"Jung","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Kumoh National Institute of Technology (KIT), Gumi, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","year":"0","journal-title":"Extract Loudest Section"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1009"},{"key":"ref31","first-page":"784","article-title":"Know what you Don’t know: Unanswerable questions for SQuAD","author":"rajpurkar","year":"2018","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref36","article-title":"Gaussian error linear units (GELUs)","author":"hendrycks","year":"2016","journal-title":"arXiv 1606 08415"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053889"},{"key":"ref34","article-title":"Howl: A deployed, open-source wake word detection system","author":"tang","year":"2020","journal-title":"arXiv 2008 09606"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854370"},{"key":"ref40","year":"0","journal-title":"Split Algorithm"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1737"},{"key":"ref12","article-title":"Hello edge: Keyword spotting on microcontrollers","author":"zhang","year":"2017","journal-title":"arXiv 1711 07128"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462688"},{"key":"ref14","article-title":"A neural attention model for speech command recognition","author":"coimbra de andrade","year":"2018","journal-title":"arXiv 1808 08929"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2204"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-480"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1393"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2891838"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1363"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1109\/SLT48900.2021.9383575","article-title":"Audio albert: A lite bert for self-supervised learning of audio representation","author":"chi","year":"2021","journal-title":"Proc IEEE Spoken Lang Technol Workshop (SLT)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2947"},{"key":"ref27","year":"2020","journal-title":"Speech commands dataset version 2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"ref6","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"zhang","year":"2020","journal-title":"arXiv 2010 10504"},{"key":"ref29","first-page":"1","article-title":"Electra: Pre-training text encoders as discriminators rather than generators","author":"clark","year":"2020","journal-title":"Proc ICLR Conf"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref2","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref9","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1058"},{"key":"ref22","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"warden","year":"2018","journal-title":"arXiv 1804 03209"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1003"},{"key":"ref42","article-title":"Multi-layer attention mechanism for speech keyword recognition","author":"luo","year":"2019","journal-title":"arXiv 1907 04536"},{"key":"ref24","article-title":"DetNet: A backbone network for object detection","author":"li","year":"2018","journal-title":"arXiv 1804 06215"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053193"},{"key":"ref26","year":"2020","journal-title":"Speech commands dataset version 1"},{"key":"ref43","first-page":"17","article-title":"An automatic data construction approach for Korean speech command recognition","volume":"24","author":"lim","year":"2019","journal-title":"J Korean Soc Comput Inf"},{"key":"ref25","first-page":"3320","article-title":"How transferable are features in deep neural networks?","author":"yosinski","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst (NIPS)"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09427206.pdf?arnumber=9427206","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T19:54:18Z","timestamp":1776369258000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9427206\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3078715","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}