{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T17:13:03Z","timestamp":1777050783129,"version":"3.51.4"},"reference-count":31,"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\/501100006730","name":"Romanian Ministry of Education and Research, CNCS - UEFISCDI","doi-asserted-by":"publisher","award":["PN-III-P1-1.1-TE-2019-0420"],"award-info":[{"award-number":["PN-III-P1-1.1-TE-2019-0420"]}],"id":[{"id":"10.13039\/501100006730","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006730","name":"Romanian Ministry of Education and Research, CNCS - UEFISCDI","doi-asserted-by":"publisher","award":["PNCDI III"],"award-info":[{"award-number":["PNCDI III"]}],"id":[{"id":"10.13039\/501100006730","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.2021.3119201","type":"journal-article","created":{"date-parts":[[2021,10,10]],"date-time":"2021-10-10T22:57:43Z","timestamp":1633906663000},"page":"139544-139555","source":"Crossref","is-referenced-by-count":5,"title":["Automatic Subtitle Synchronization and Positioning System Dedicated to Deaf and Hearing Impaired People"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8010-9943","authenticated-orcid":false,"given":"Bogdan","family":"Mocanu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3170-4150","authenticated-orcid":false,"given":"Ruxandra","family":"Tapu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2870334"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IPTA.2017.8310091"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"1516","DOI":"10.21437\/Interspeech.2013-306","article-title":"Technique for automatic sentence level alignment of long speech and transcripts","author":"ahmed","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref11","first-page":"3154","article-title":"Efficient harvesting of Internet audio for resource-scarce ASR","author":"davel","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref12","first-page":"1","article-title":"Rapid building of an ASR system for under-resourced languages based on multilingual unsupervised training","author":"vu","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"1405","DOI":"10.21437\/Interspeech.2014-345","article-title":"Audio-to-text alignment for speech recognition with very limited resources","author":"anguera","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref14","year":"2021","journal-title":"The Kaldi Speech Recognition Toolkit"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178960"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2505140"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3172944.3172984"},{"key":"ref18","author":"yu","year":"2014","journal-title":"Automatic Speech Recognition?A Deep Learning Approach"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref28","year":"2021","journal-title":"Subtitle guidelines"},{"key":"ref4","first-page":"2711","article-title":"A recursive algorithm for the forced alignment of very long audio segments","author":"moreno","year":"1998","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref27","article-title":"Towards end-to-end speech recognition with deep convolutional neural networks","author":"zhang","year":"2017","journal-title":"arXiv 1701 02720"},{"key":"ref3","first-page":"1","article-title":"Audio and text synchronization for TV news subtitling based on automatic speech recognition","author":"garcia","year":"2009","journal-title":"Proc IEEE Int Symp Broadband Multimedia Syst Broadcast"},{"key":"ref6","first-page":"1","article-title":"Automatic alignment and error correction of human generated transcripts for long speech recordings","author":"hazen","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.283"},{"key":"ref5","first-page":"1","article-title":"SailAlign: Robust long speech-text alignment","author":"katsamanis","year":"2011","journal-title":"Proc Workshop New Tools Methods Very-Large Scale Phonetics Res"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2007.4284627"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-611"},{"key":"ref2","year":"2021","journal-title":"World Health Organization Deafness and hearing loss"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1520","DOI":"10.21437\/Interspeech.2013-307","article-title":"Text-to-speech alignment of long recordings using universal phone models","author":"hoffmann","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2578726.2578760"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2915581"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"2633","DOI":"10.21437\/Interspeech.2018-1096","article-title":"Punctuation prediction model for conversational speech","author":"?elasko","year":"2018","journal-title":"Proc INTERSPEECH"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1117\/12.526823"},{"key":"ref23","year":"2021","journal-title":"The Recommendation of the Conseil supérieur de l’audiovisuel (CSA)"},{"key":"ref26","article-title":"Automatic closed caption alignment based on speech recognition transcripts","author":"huang","year":"2003"},{"key":"ref25","year":"2021","journal-title":"The Open Source Speech Recognition Toolkit (CMUSphinx) Project"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09565923.pdf?arnumber=9565923","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:51:12Z","timestamp":1725904272000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9565923\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3119201","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}