{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T15:06:53Z","timestamp":1790262413969,"version":"4.1.0"},"reference-count":50,"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"}],"funder":[{"DOI":"10.13039\/501100002661","name":"Fonds De La Recherche Scientifique - FNRS","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2016,1]]},"DOI":"10.1109\/taslp.2015.2456421","type":"journal-article","created":{"date-parts":[[2015,7,14]],"date-time":"2015-07-14T19:50:48Z","timestamp":1436903448000},"page":"5-15","source":"Crossref","is-referenced-by-count":32,"title":["HMM-Based Speech Segmentation: Improvements of Fully Automatic Approaches"],"prefix":"10.1109","volume":"24","author":[{"given":"Sandrine","family":"Brognaux","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Drugman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.09.001"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"693","DOI":"10.21437\/Eurospeech.1991-183","article-title":"A preliminary statistical evaluation of manual and automatic segmentation discrepancies","author":"cosi","year":"1991","journal-title":"Proc EUROSPEECH"},{"key":"ref33","article-title":"Sailalign: Robust long speech-text alignment","author":"katsamanis","year":"2011","journal-title":"Proc Workshop New Tools Meth for Very Large Scale Res Phon Sci"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.903933"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.07.001"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1007\/3-540-46154-X_38","author":"demuynck","year":"2002","journal-title":"Text Speech and Dialogue"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607054"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-009-9038-4"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.11.003"},{"key":"ref34","author":"young","year":"1995","journal-title":"The HTK Book (for HTK Version 3)"},{"key":"ref28","first-page":"149","article-title":"Refined speech segmentation for concatenative speech synthesis","author":"sethy","year":"2002","journal-title":"Proc ICSLP"},{"key":"ref27","first-page":"759","article-title":"Evaluating factors impacting the accuracy of forced alignments in a multimodal corpus","author":"chen","year":"2004","journal-title":"Proc LREC"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367224"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1997-664","article-title":"High-quality speech synthesis for phonetic speech segmentation","author":"malfr\ufffdre","year":"1997","journal-title":"Proc EUROSPEECH"},{"key":"ref22","first-page":"93","article-title":"An HMM-based system for automatic segmentation and alignment of speech","author":"sj\ufffdlander","year":"2003","journal-title":"Proc Fonetik"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90083-W"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1983.1171971"},{"key":"ref23","article-title":"HMMs for automatic phonetic segmentation","author":"toledano","year":"2002","journal-title":"Proc LREC"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1894-4_25"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30228-5_4"},{"key":"ref50","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2005-792","article-title":"Linguistic features weighting for a text-to-speech system without prosody model","author":"colotte","year":"2005","journal-title":"Proc INTERSPEECH"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-815","article-title":"EasyAlign: An automatic phonetic alignment tool under Praat","author":"goldman","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref11","article-title":"Speech phonetization alignment and syllabification (SPPAS): A tool for the automatic analysis of speech prosody","author":"bigi","year":"2012","journal-title":"Proc Speech Prosody"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1993-329","article-title":"Automatic segmentation of speech for TTS","author":"ljolje","year":"1993","journal-title":"Proc EUROSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415112"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2009-266","article-title":"Phonetic alignment for speech synthesis in under-resourced languages","author":"van niekerk","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33983-7_30"},{"key":"ref15","article-title":"Easyalign spanish: An (semi-) automatic segmentation tool under praat","author":"goldman","year":"2011","journal-title":"Proc 5th Congr de Fontica Experim"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1999-703","article-title":"High-accuracy automatic segmentation","author":"van santen","year":"1999","journal-title":"Proc EUROSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1121\/1.3277194"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424260"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1981.1171095"},{"key":"ref4","first-page":"464","article-title":"Wavesurfer - an open-source speech tool","author":"sj\ufffdlander","year":"2000","journal-title":"Proc ICSLP"},{"key":"ref3","author":"jelinek","year":"1997","journal-title":"Statistical Methods for Speech Recognition"},{"key":"ref6","article-title":"Elan: A professional framework for multimodality research","author":"wittenburg","year":"2006","journal-title":"Proc LREC"},{"key":"ref5","author":"boersma","year":"2009","journal-title":"Praat Doing Phonetics by Computer (Version 5 1 05) [Computer Program]"},{"key":"ref8","article-title":"Statistical modeling of pronunciation: It?s not the model, it?s the data","author":"schiel","year":"1998","journal-title":"Proc ISCA Modeling Pronunciat Variat for Autom Speech Recogn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326076"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1121\/1.2935783"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1894-4_24"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947382"},{"key":"ref45","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-519","article-title":"Joint robust voicing detection and pitch estimation based on residual harmonics","author":"drugman","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref48","article-title":"A new prosody annotation protocol for live sports commentaries","author":"brognaux","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.608022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref41","first-page":"165","article-title":"Alignement automatique et analyse phon\ufffdtique: Comparaison de diff\ufffdrents syst\ufffdmes pour l?analyse du schwa","volume":"49","author":"burki","year":"2008","journal-title":"Traitement Automatique des Langues"},{"key":"ref44","article-title":"Improved differential phase spectrum processing for formant tracking","author":"bozkurt","year":"2004","journal-title":"Proc ICSLP"},{"key":"ref43","author":"peeters","year":"2004","journal-title":"?A Large set of audio features for sound description (similarity and classification) in the CUIDADO project ?"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7322312\/7156110.pdf?arnumber=7156110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T05:45:39Z","timestamp":1748497539000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7156110\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,1]]},"references-count":50,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2015.2456421","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,1]]}}}