{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:21:32Z","timestamp":1740169292792,"version":"3.37.3"},"reference-count":48,"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-nc-nd\/4.0\/"}],"funder":[{"name":"Information Technology Research Center (ITRC) Support Program through the Institute of Information & Communications Technology Planning & Evaluation"},{"name":"Korean Government","award":["IITP-2021-2020-0-01808"],"award-info":[{"award-number":["IITP-2021-2020-0-01808"]}]},{"DOI":"10.13039\/501100003621","name":"Ministry of Science and ICT","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003621","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MIST through the IITP Program","award":["2019-0-00004"],"award-info":[{"award-number":["2019-0-00004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3115608","type":"journal-article","created":{"date-parts":[[2021,9,24]],"date-time":"2021-09-24T20:50:05Z","timestamp":1632516605000},"page":"136476-136486","source":"Crossref","is-referenced-by-count":4,"title":["Linguistic-Coupled Age-to-Age Voice Translation to Improve Speech Recognition Performance in Real Environments"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0111-300X","authenticated-orcid":false,"given":"June-Woo","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1507-5967","authenticated-orcid":false,"given":"Hyekyung","family":"Yoon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0398-831X","authenticated-orcid":false,"given":"Ho-Young","family":"Jung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"5410","article-title":"Almost unsupervised text to speech and automatic speech recognition","author":"ren","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054523"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.12.035"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2015.09.002"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.818026"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1066"},{"key":"ref36","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207653"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1789"},{"key":"ref10","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403331"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref12","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","author":"amodei","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref17","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"arXiv 1807 03748"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1997-623","article-title":"Automatic speech recognition for children","author":"potamianos","year":"1997","journal-title":"Proc EUROSPEECH"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541104"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424210"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758083"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"ref8","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014","journal-title":"arXiv 1412 5567"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref1","first-page":"39","article-title":"Deep belief networks for phone recognition","volume":"1","author":"mohamed","year":"2009","journal-title":"Proc NIPS Workshop Deep Learn Speech Recognit Rel Appl"},{"key":"ref46","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref45","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":"ref22","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref48","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref21","article-title":"End-to-end ASR: From supervised to semi-supervised learning with modern architectures","author":"synnaeve","year":"2019","journal-title":"arXiv 1911 08460"},{"key":"ref42","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","author":"maddison","year":"2016","journal-title":"arXiv 1611 00712"},{"key":"ref24","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2016","journal-title":"arXiv 1611 01144"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref26","first-page":"344","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":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref25","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"zhang","year":"2020","journal-title":"arXiv 2010 10504"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09548063.pdf?arnumber=9548063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T03:16:24Z","timestamp":1673320584000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9548063\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3115608","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}