{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:58:06Z","timestamp":1774418286185,"version":"3.50.1"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319439570","type":"print"},{"value":"9783319439587","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-43958-7_7","type":"book-chapter","created":{"date-parts":[[2016,8,12]],"date-time":"2016-08-12T02:11:41Z","timestamp":1470967901000},"page":"67-74","source":"Crossref","is-referenced-by-count":2,"title":["A Phonetic Segmentation Procedure Based on Hidden Markov Models"],"prefix":"10.1007","author":[{"given":"Edvin","family":"Pakoci","sequence":"first","affiliation":[]},{"given":"Branislav","family":"Popovi\u0107","sequence":"additional","affiliation":[]},{"given":"Nik\u0161a","family":"Jakovljevi\u0107","sequence":"additional","affiliation":[]},{"given":"Darko","family":"Pekar","sequence":"additional","affiliation":[]},{"given":"Fathy","family":"Yassa","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,8,13]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Brognaux, S., Roekhaut, S., Drugman, T., Beaufort, R.: Train&Align: a new online tool for automatic phonetic alignment. In: Spoken Language Technology Workshop (SLT), pp. 416\u2013421. IEEE Signal Processing Society (2012)","DOI":"10.1109\/SLT.2012.6424260"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Scharenborg, O., Ernestus, M., Wan, V.: Segmentation of speech: child\u2019s play? In: 8th Annual Conference of the International Speech Communication Association (INTERSPEECH), Antwerp, pp. 1953\u20131956 (2007)","DOI":"10.21437\/Interspeech.2007-47"},{"key":"7_CR3","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1007\/11520153_12","volume-title":"Nonlinear Speech Modeling and Applications","author":"A Esposito","year":"2005","unstructured":"Esposito, A., Aversano, G.: Text independent methods for speech segmentation. In: Chollet, G., Esposito, A., Faundez-Zanuy, M., Marinaro, M. (eds.) Nonlinear Speech Modeling. LNCS (LNAI), vol. 3445, pp. 261\u2013290. Springer, Heidelberg (2005)"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Leow, S.J., Chng, E.S., Lee, C.H.: Language-resource independent speech segmentation using cues from a spectrogram image. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), South Brisbane, pp. 5813\u20135817 (2015)","DOI":"10.1109\/ICASSP.2015.7179086"},{"issue":"1","key":"7_CR5","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/s10772-015-9320-6","volume":"19","author":"S Priyadarsini","year":"2016","unstructured":"Priyadarsini, S., Kumar, A.: Automatic speech segmentation in syllable centric speech recognition system. J. Speech Technol. 19(1), 9\u201318 (2016)","journal-title":"J. Speech Technol."},{"issue":"2","key":"7_CR6","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1109\/TASL.2008.2009162","volume":"17","author":"G Almpanidis","year":"2009","unstructured":"Almpanidis, G., Kotti, M., Kotropoulos, C.: Robust detection of phone boundaries using model selection criteria with few observations. IEEE Trans. Audio Speech Lang. Process. 17(2), 287\u2013298 (2009). IEEE Signal Processing Society","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"7_CR7","unstructured":"Bigi, B.: SPPAS: a tool for the phonetic segmentations of speech. In: 8th International Conference on Language Resources and Evaluation (LREC), Istanbul, pp. 1748\u20131755 (2012)"},{"key":"7_CR8","unstructured":"Boeffard, O., Charonnat, L., Le Maguer, S., Lolive, D., Vidal, G.: Towards fully automatic annotation of audio books for TTS. In: 8th International Conference on Language Resources and Evaluation (LREC), Instanbul, pp. 975\u2013980 (2012)"},{"issue":"1","key":"7_CR9","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1109\/TASLP.2015.2456421","volume":"24","author":"S Brognaux","year":"2016","unstructured":"Brognaux, S., Drugman, T.: HMM-based speech segmentation: improvements of fully automatic approaches. IEEE\/ACM Trans. Audio Speech Lang. Process. 24(1), 5\u201315 (2016). IEEE Signal Processing Society","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Hoffmann, S., Pfister, B.: Fully automatic segmentation for prosodic speech corpora. In: 10th Annual Conference of the International Speech Communication Association (INTERSPEECH), Makuhari, pp. 1389\u20131392 (2010)","DOI":"10.21437\/Interspeech.2010-423"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Hoffmann, S., Pfister, B.: Text-to-speech alignment of long recordings using universal phone models. In: 14th Annual Conference of the International Speech Communication Association (INTERSPEECH), Lyon, pp. 1520\u20131524 (2013)","DOI":"10.21437\/Interspeech.2013-307"},{"key":"7_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1007\/978-3-642-04208-9_27","volume-title":"Text, Speech and Dialogue","author":"J Matou\u0161ek","year":"2009","unstructured":"Matou\u0161ek, J.: Automatic pitch-synchronous phonetic segmentation with context-independent HMMs. In: Matou\u0161ek, V., Mautner, P. (eds.) TSD 2009. LNCS, vol. 5729, pp. 178\u2013185. Springer, Heidelberg (2009)"},{"key":"7_CR13","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1016\/j.csl.2015.06.006","volume":"35","author":"A Stan","year":"2016","unstructured":"Stan, A., Mamiya, Y., Yamagishi, J., Bell, P., Watts, O., Clark, R.A.J., King, S.: ALISA: an automatic lightly supervised speech segmentation and alignment tool. J. Comput. Speech Lang. 35, 116\u2013133 (2016)","journal-title":"J. Comput. Speech Lang."},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Adell, J., Bonafonte, A., Gomez, J., Castro, M.: Comparative study of automatic phone segmentation methods for TTS. In: 30th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Philadelphia, pp. 309\u2013312 (2005)","DOI":"10.1109\/ICASSP.2005.1415112"},{"issue":"6","key":"7_CR15","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1109\/TSA.2003.813579","volume":"11","author":"D Toledano","year":"2003","unstructured":"Toledano, D., Gomez, L., Grande, L.: Automatic phonetic segmentation. IEEE Trans. Speech Audio Process. 11(6), 617\u2013625 (2003). IEEE Signal Processing Society","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"7_CR16","unstructured":"Wang, L., Zhao, Y., Chu, M., Zhou, J., Cao, Z.: Refining segmental boundaries for TTS database using fine contextual-dependent boundary models. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Montreal, pp. 641\u2013644 (2004)"},{"issue":"4","key":"7_CR17","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1016\/0167-6393(93)90083-W","volume":"12","author":"F Brugnara","year":"1993","unstructured":"Brugnara, F., Falavigna, D., Omologo, M.: Automatic segmentation and labeling of speech based on hidden Markov models. J. Speech Commun. 12(4), 357\u2013370 (1993)","journal-title":"J. Speech Commun."},{"key":"7_CR18","unstructured":"Appen, Product Catalog. http:\/\/catalog.appenbutlerhill.com\/"},{"key":"7_CR19","unstructured":"Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motl\u00edcek, P., Qian, Y., Schwarz, P., Silovsk\u00fd, J., Stemmer, G., Vesel\u00fd, K.: The kaldi speech recognition toolkit. In: IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 1\u20134. IEEE Signal Processing Society (2011)"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-43958-7_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,5]],"date-time":"2022-07-05T21:07:05Z","timestamp":1657055225000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-43958-7_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319439570","9783319439587"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-43958-7_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]}}}