{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T23:54:27Z","timestamp":1778716467408,"version":"3.51.4"},"reference-count":17,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2012,12,22]],"date-time":"2012-12-22T00:00:00Z","timestamp":1356134400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2014,9]]},"DOI":"10.1007\/s11042-012-1318-3","type":"journal-article","created":{"date-parts":[[2012,12,21]],"date-time":"2012-12-21T04:32:41Z","timestamp":1356064361000},"page":"21-40","source":"Crossref","is-referenced-by-count":24,"title":["An automatic caption alignment mechanism for off-the-shelf speech recognition technologies"],"prefix":"10.1007","volume":"72","author":[{"given":"Maria","family":"Federico","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Furini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,12,22]]},"reference":[{"key":"1318_CR1","unstructured":"Canadian\u00a0Association of\u00a0Broadcasters (2008) Closed captioning standards and protocol for canadian english language television programming services. In: CAB\u2019s closed captioning manual"},{"key":"1318_CR2","unstructured":"Carnegie Mellon University CMU-Sphinx\u2014open source toolkit for speech recognition. http:\/\/cmusphinx.sourceforge.net\/wiki . Accessed 19 Sep 2012"},{"key":"1318_CR3","doi-asserted-by":"crossref","unstructured":"Federico M, Furini M (2012) Enhancing learning accessibility through fully automatic captioning. In: Proceedings of the international cross-disciplinary conference on web accessibility, W4A \u201912. New York, NY, USA, ACM, pp\u00a040:1\u201340:4","DOI":"10.1145\/2207016.2207053"},{"issue":"2","key":"1318_CR4","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1109\/TCE.2008.4560123","volume":"54","author":"M Furini","year":"2008","unstructured":"Furini M (2008) Fast play: A novel feature for digital consumer video devices. IEEE Trans Consum Electron 54(2):513\u2013520","journal-title":"IEEE Trans Consum Electron"},{"issue":"3","key":"1318_CR5","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1111\/j.1944-9720.1991.tb00469.x","volume":"24","author":"T Garza","year":"1991","unstructured":"Garza T (1991) Evaluating the use of captioned video materials in advanced foreign language learning. Foreign Lang Ann 24(3):239\u2013258","journal-title":"Foreign Lang Ann"},{"key":"1318_CR6","doi-asserted-by":"crossref","unstructured":"Haubold A, Kender JR (2007) Alignment of speech to highly imperfect text transcriptions. In: Proceedings of the 2007 IEEE international conference on multimedia and expo, ICME 2007. IEEE, Beijing, China, pp\u00a0224\u2013227, 2\u20135\u00a0July 2007","DOI":"10.1109\/ICME.2007.4284627"},{"key":"1318_CR7","doi-asserted-by":"crossref","unstructured":"Hong R, Wang M, Xu M, Yan S, Chua TS (2010) Dynamic captioning: video accessibility enhancement for hearing impairment. In: Proceedings of the international conference on multimedia, MM \u201910. New York, NY, USA, ACM, pp 421\u2013430","DOI":"10.1145\/1873951.1874013"},{"key":"1318_CR8","unstructured":"Huang CW, Hsu W, Chang SF (2003) Automatic closed caption alignment based on speech recognition transcripts. Technical report, Columbia University"},{"issue":"1","key":"1318_CR9","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1093\/deafed\/6.1.43","volume":"6","author":"L Jelinek","year":"2001","unstructured":"Jelinek L, Jackson DW (2001) Television literacy: comprehension of program content using closed captions for the deaf. J Deaf Stud Deaf Educ 6(1):43\u201353","journal-title":"J Deaf Stud Deaf Educ"},{"key":"1318_CR10","volume-title":"Acoustic and auditory phonetics","author":"K Johnson","year":"2011","unstructured":"Johnson K (2011) Acoustic and auditory phonetics, 3rd edn. Wiley-Blackwell, Malden","edition":"3"},{"key":"1318_CR11","doi-asserted-by":"crossref","unstructured":"Kemp T, Schmidt M, Westphal M, Waibel A (2000) Strategies for automatic segmentation of audio data. In: Proceedings of the international IEEE conference on acoustics, speech, and signal processing (ICASSP), pp 1423\u20131426","DOI":"10.1109\/ICASSP.2000.861862"},{"key":"1318_CR12","doi-asserted-by":"crossref","unstructured":"Kim SK, Hwang DS, Kim JY, Seo YS (2005) An effective news anchorperson shot detection method based on adaptive audio\/visual model generation. In: Proceedings of the international conference on image and video retrieval (CIVR), pp\u00a0276\u2013285","DOI":"10.1007\/11526346_31"},{"issue":"2","key":"1318_CR13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.4018\/jmdem.2010040101","volume":"1","author":"A Knight","year":"2010","unstructured":"Knight A, Almeroth KC (2010) Fast caption alignment for automatic indexing of audio. Int J Multimed Data Eng Manag 1(2):1\u201317","journal-title":"Int J Multimed Data Eng Manag"},{"key":"1318_CR14","unstructured":"Martone AF, Taskiran, CM, Delp EJ (2004) Automated closed-captioning using text alignment. In: SPIE Proceedings of Storage and retrieval methods and applications for multimedia, vol\u00a05307. SPIE, pp 108\u2013116"},{"key":"1318_CR15","unstructured":"Reager SE (2009) Closed captioning for online video. In: Streaming media industry sourcebook, pp 100\u2013102"},{"key":"1318_CR16","unstructured":"Shimogori N, Ikeda T, Tsuboi S (2010) Automatically generated captions: will they help non-native speakers communicate in english? In: Proceedings of the 3rd international conference on intercultural collaboration, ICIC \u201910. New York, NY, USA, ACM, pp\u00a079\u201386"},{"issue":"3","key":"1318_CR17","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1109\/TITB.2006.885549","volume":"11","author":"X Zhang","year":"2007","unstructured":"Zhang X, Zhao Y, Schopp L (2007) A novel method of language modeling for automatic captioning in tc video teleconferencing. IEEE Trans Inf Technol Biomed 11(3):332\u2013337","journal-title":"IEEE Trans Inf Technol Biomed"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-012-1318-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-012-1318-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-012-1318-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,7]],"date-time":"2019-07-07T11:50:57Z","timestamp":1562500257000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-012-1318-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,12,22]]},"references-count":17,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,9]]}},"alternative-id":["1318"],"URL":"https:\/\/doi.org\/10.1007\/s11042-012-1318-3","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,12,22]]}}}