{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T12:41:22Z","timestamp":1771332082392,"version":"3.50.1"},"reference-count":19,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2016,1]]},"DOI":"10.1109\/lsp.2015.2505140","type":"journal-article","created":{"date-parts":[[2015,12,3]],"date-time":"2015-12-03T19:06:27Z","timestamp":1449169587000},"page":"126-129","source":"Crossref","is-referenced-by-count":12,"title":["Probabilistic Kernels for Improved Text-to-Speech Alignment in Long Audio Tracks"],"prefix":"10.1109","volume":"23","author":[{"given":"German","family":"Bordel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mikel","family":"Penagarikano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luis Javier","family":"Rodriguez-Fuentes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aitor","family":"Alvarez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amparo","family":"Varona","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960722"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-402","article-title":"A simple and efficient method to align very long speech signals to acoustically imperfect transcriptions","author":"bordel","year":"2012","journal-title":"Proc Interspeech 2012"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1613","DOI":"10.21437\/Interspeech.2011-483","article-title":"Automatic subtitling of the basque parliament plenary sessions videos","author":"bordel","year":"2011","journal-title":"Proc Interspeech 2011"},{"key":"ref13","author":"graff","year":"2002","journal-title":"1997 HUB4 English evaluation speech and transcripts"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/360825.360861"},{"key":"ref15","first-page":"707","article-title":"Binary codes capable of correcting deletions, insertions, and reversals","volume":"10","author":"levenshtein","year":"1966","journal-title":"Sov Phys Doklady"},{"key":"ref16","first-page":"6280","article-title":"Long audio alignment for automatic subtitling using different phone-relatedness measures","author":"\ufffdlvarez","year":"2014","journal-title":"Proc IEEE ICASSP"},{"key":"ref17","author":"garofolo","year":"1993","journal-title":"TIMIT Acoustic-Phonetic Continuous Speech Corpus"},{"key":"ref18","author":"garofolo","year":"2007","journal-title":"CSRI (WSJ0) Complete"},{"key":"ref19","author":"kondrak","year":"2002","journal-title":"Algorithms for Language Reconstruction"},{"key":"ref4","first-page":"1606","article-title":"Automatic alignment and error correction of human generated transcripts for long speech recordings","author":"hazen","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref3","article-title":"A recursive algorithm for the forced alignment of very long audio segments","author":"moreno","year":"1998","journal-title":"Proc Fifth Int l Conf Spoken Language Processing"},{"key":"ref6","article-title":"Sailalign: Robust long speech-text alignment","author":"katsamanis","year":"2011","journal-title":"Proc of Workshop on New Tools and Methods for Very Large Scale Research in Phonetic Sciences"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2007.4284627"},{"key":"ref8","first-page":"1516","article-title":"Technique for automatic sentence level alignment of long speech and transcripts","author":"ahmed","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref7","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 2013"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"903","DOI":"10.21437\/Eurospeech.1997-300","article-title":"Automatic generation of hyperlinks between audio and transcript","author":"robert-ribes","year":"1997","journal-title":"Proc Fifth European Conf Speech Comm and Technology"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1894-4_25"},{"key":"ref9","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 2014"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/7314997\/7346429.pdf?arnumber=7346429","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,16]],"date-time":"2023-08-16T01:48:00Z","timestamp":1692150480000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7346429\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,1]]},"references-count":19,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/lsp.2015.2505140","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,1]]}}}