{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,5,26]],"date-time":"2023-05-26T10:10:26Z","timestamp":1685095826209},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2008,6,1]],"date-time":"2008-06-01T00:00:00Z","timestamp":1212278400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2008,6]]},"DOI":"10.1007\/s10772-009-9038-4","type":"journal-article","created":{"date-parts":[[2009,8,13]],"date-time":"2009-08-13T12:12:51Z","timestamp":1250165571000},"page":"73-85","source":"Crossref","is-referenced-by-count":6,"title":["Phonetic segmentation using multiple speech features"],"prefix":"10.1007","volume":"11","author":[{"given":"Iosif","family":"Mporas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Todor","family":"Ganchev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikos","family":"Fakotakis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2009,8,14]]},"reference":[{"key":"9038_CR1","doi-asserted-by":"crossref","unstructured":"Adami, A. G., & Hermansky, H. (2003). Segmentation of speech for speaker and language recognition. In Proceedings of the 8th European conference on speech communication and technology (EUROSPEECH 2003) (pp.\u00a0841\u2013844).","DOI":"10.21437\/Eurospeech.2003-189"},{"key":"9038_CR2","doi-asserted-by":"crossref","unstructured":"Adell, J., Bonafonte, A., Gomez, J. A., & Castro, M. J. (2005). Comparative study of automatic phone segmentation methods for TTS. In Proceedings of the 2005 IEEE international conference on acoustics, speech, and signal processing (ICASSP 2005) (pp.\u00a0309\u2013312).","DOI":"10.1109\/ICASSP.2005.1415112"},{"key":"9038_CR3","doi-asserted-by":"crossref","unstructured":"Aversano, G., Esposito, A., Esposito, A., & Marinaro, M. (2001). A\u00a0new text-independent method for phoneme segmentation. In Proceedings of the 44th IEEE Midwest symposium on circuits and systems (Vol.\u00a02, pp.\u00a0516\u2013519).","DOI":"10.1109\/MWSCAS.2001.986241"},{"key":"9038_CR4","doi-asserted-by":"crossref","unstructured":"Bajwa, R. S., Owens, R. M., & Kelliher, T. P. (1996). Simultaneous speech segmentation and phoneme recognition using dynamic programming. In Proceedings of the 1996 IEEE international conference on acoustics, speech, and signal processing (ICASSP 1996) (Vol.\u00a06, pp.\u00a03213\u20133216).","DOI":"10.1109\/ICASSP.1996.550560"},{"issue":"1","key":"9038_CR5","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1214\/aoms\/1177697196","volume":"41","author":"L. E. Baum","year":"1970","unstructured":"Baum, L. E., Petrie, T., Soules, G., & Weiss, N. (1970). A\u00a0maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains. Annals of Mathematical Statistics, 41(1), 164\u2013171.","journal-title":"Annals of Mathematical Statistics"},{"key":"9038_CR6","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. (1993). Automatic segmentation and labeling of speech based on hidden Markov models. Speech Communication, 12, 357\u2013370.","journal-title":"Speech Communication"},{"key":"9038_CR7","doi-asserted-by":"crossref","unstructured":"Dalsgaard, P., Andersen, O., & Barry, W. (1991). Multi-lingual label alignment using acoustic-phonetic features derived by neural-network technique. In Proceedings of the 1991 IEEE international conference on acoustics, speech, and signal processing (ICASSP 1991) (Vol.\u00a01, pp.\u00a0197\u2013200).","DOI":"10.1109\/ICASSP.1991.150311"},{"issue":"4","key":"9038_CR8","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"S. B. Davis","year":"1980","unstructured":"Davis, S. B., & Mermelstein, P. (1980). Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Transactions on Acoustics, Speech and Signal Processing, 28(4), 357\u2013366.","journal-title":"IEEE Transactions on Acoustics, Speech and Signal Processing"},{"key":"9038_CR9","volume-title":"Discrete-time processing of speech signals","author":"J. Deller","year":"1993","unstructured":"Deller, J., Hansen, J., & Proakis, J. (1993). Discrete-time processing of speech signals. New York: Macmillan Publishing."},{"key":"9038_CR10","unstructured":"ETSI (2007). ETSI ES 202 050, V1.1.5 (2007-1). ETSI standard: speech processing, transmission and quality aspects (STQ); Distributed speech recognition; Extended advanced front-end feature extraction algorithm; Compression algorithms; Back-end speech reconstruction algorithm, January 2007 (Sect.\u00a05.3, pp.\u00a021\u201324)."},{"issue":"7","key":"9038_CR11","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1109\/97.928676","volume":"8","author":"O. Farooq","year":"2001","unstructured":"Farooq, O., & Datta, S. (2001). Mel filter-like admissible wavelet packet structure for speech recognition. IEEE Signal Processing Letters, 8(7), 196\u2013198.","journal-title":"IEEE Signal Processing Letters"},{"key":"9038_CR12","unstructured":"Garofolo, J. (1988). Getting started with the DARPA-TIMIT CD-ROM: an acoustic phonetic continuous speech database. National Institute of Standards and Technology (NIST), Gaithersburgh, MD, USA."},{"key":"9038_CR13","doi-asserted-by":"crossref","unstructured":"Grayden, D. B., & Scordilis, M. S. (1994). Phonemic segmentation of fluent speech. In Proceedings of the 1994 IEEE international conference on acoustics, speech, and signal processing (ICASSP 1994) (Vol.\u00a01, pp.\u00a073\u201376).","DOI":"10.1109\/ICASSP.1994.389352"},{"issue":"4","key":"9038_CR14","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1121\/1.399423","volume":"87","author":"H. Hermansky","year":"1990","unstructured":"Hermansky, H. (1990). Perceptual linear predictive (PLP) analysis for speech. Journal of the Acoustical Society of America, 87(4), 1738\u20131752.","journal-title":"Journal of the Acoustical Society of America"},{"key":"9038_CR15","doi-asserted-by":"crossref","unstructured":"Hosom, J.-P. (2002). Automatic phoneme alignment based on acoustic-phonetic modeling. In Proceedings of the 7th international conference on spoken language processing (ICSLP 2002) (pp.\u00a0357\u2013360).","DOI":"10.21437\/ICSLP.2002-154"},{"issue":"Suppl.\u00a01","key":"9038_CR16","doi-asserted-by":"crossref","first-page":"S35","DOI":"10.1121\/1.1995189","volume":"57","author":"F. Itakura","year":"1975","unstructured":"Itakura, F. (1975). Line spectrum representation of linear predictive coefficients. Journal of the Acoustical Society of America, 57(Suppl.\u00a01), S35.","journal-title":"Journal of the Acoustical Society of America"},{"key":"9038_CR17","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/j.specom.2007.07.001","volume":"50","author":"S. Jarifi","year":"2008","unstructured":"Jarifi, S., Pastor, D., & Rosec, O. (2008). A fusion approach for automatic speech segmentation of large corpora with application to speech synthesis. Speech Communication, 50, 67\u201380.","journal-title":"Speech Communication"},{"key":"9038_CR18","doi-asserted-by":"crossref","unstructured":"Kawai, H., & Toda, T. (2004). An evaluation of automatic phone segmentation for concatenative speech synthesis. In Proceedings of the 2004 IEEE international conference on acoustics, speech, and signal processing (ICASSP 2004) (Vol.\u00a01, pp.\u00a0667\u2013680).","DOI":"10.1109\/ICASSP.2004.1326076"},{"issue":"8","key":"9038_CR19","doi-asserted-by":"crossref","first-page":"2373","DOI":"10.1109\/TASL.2007.903928","volume":"15","author":"J. Keshet","year":"2007","unstructured":"Keshet, J., Shalev-Shwartz, S., Singer, Y., & Chazan, D. (2007). A large margin algorithm for speech-to-phoneme and music-to-score alignment. IEEE Transactions on Audio, Speech, and Language Processing, 15(8), 2373\u20132382.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9038_CR20","doi-asserted-by":"crossref","unstructured":"Kim, Y.-J., & Conkie, A. (2002). Automatic segmentation combining an HMM-based approach and spectral boundary correction. In Proceedings of the 7th international conference on spoken language processing (ICSLP 2002) (pp.\u00a0145\u2013148).","DOI":"10.21437\/ICSLP.2002-88"},{"key":"9038_CR21","doi-asserted-by":"crossref","unstructured":"Kominek, J., & Black, A. (2004). A family-of-models approach to HMM-based segmentation for unit selection speech synthesis. In Proceedings of the 8th international conference on spoken language processing (ICSLP 2004) (pp.\u00a01385\u20131388).","DOI":"10.21437\/Interspeech.2004-458"},{"issue":"11","key":"9038_CR22","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.1109\/29.46546","volume":"37","author":"K.-F. Lee","year":"1989","unstructured":"Lee, K.-F., & Hon, H.-W. (1989). Speaker-independent phone recognition using hidden Markov models. IEEE Transactions on Acoustics, Speech and Signal Processing, 37(11), 1641\u20131648.","journal-title":"IEEE Transactions on Acoustics, Speech and Signal Processing"},{"key":"9038_CR23","doi-asserted-by":"crossref","unstructured":"Lin, C.-Y., Chen, K.-T., & Roger Jang, J.-S. (2005). A hybrid approach to automatic segmentation and labeling for Mandarin Chinese speech corpus. In Proceedings of the 9th European conference on speech communication and technology (EUROSPEECH 2005) (pp.\u00a01553\u20131556).","DOI":"10.21437\/Interspeech.2005-455"},{"issue":"7","key":"9038_CR24","doi-asserted-by":"crossref","first-page":"2151","DOI":"10.1109\/TASL.2007.902051","volume":"15","author":"C.-Y. Lin","year":"2007","unstructured":"Lin, C.-Y., & Jang, R. J.-S. (2007). Automatic phonetic segmentation by score predictive model for the corpora of mandarin singing voices. IEEE Transactions on Audio, Speech, and Language Processing, 15(7), 2151\u20132159.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9038_CR25","doi-asserted-by":"crossref","unstructured":"Ljolje, A., & Riley, M. D. (1991). Automatic segmentation and labeling of speech. In Proceedings of the 1991 IEEE international conference on acoustics, speech, and signal processing (ICASSP 1991) (Vol.\u00a01, pp.\u00a0473\u2013476).","DOI":"10.1109\/ICASSP.1991.150379"},{"key":"9038_CR26","first-page":"304","volume-title":"Progress in speech synthesis","author":"A. Ljolje","year":"1997","unstructured":"Ljolje, A., Hirschberg, J., & van Santen, J. P. H. (1997). Automatic speech segmentation for concatenative inventory selection. In J.\u00a0P.\u00a0H. van Santen, R. W. Sproat, J. P. Olive, & J.\u00a0Hirschberg (Eds.), Progress in speech synthesis (pp.\u00a0304\u2013311). Berlin: Springer."},{"key":"9038_CR27","doi-asserted-by":"crossref","unstructured":"Lo, H.-Y., & Wang, H.-M. (2007). Phonetic boundary refinement using support vector machine. In Proceedings of the 2007 IEEE international conference on acoustics, speech, and signal processing (ICASSP 2007) (Vol.\u00a04, pp.\u00a0933\u2013936).","DOI":"10.1109\/ICASSP.2007.367224"},{"key":"9038_CR28","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1016\/S0167-6393(02)00131-0","volume":"40","author":"F. Malfrere","year":"2003","unstructured":"Malfrere, F., Deroo, O., Dutoit, T., & Ris, C. (2003). Phonetic alignment: speech synthesis-based vs. Viterbi-based. Speech Communication, 40, 503\u2013515.","journal-title":"Speech Communication"},{"key":"9038_CR29","doi-asserted-by":"crossref","unstructured":"Matousek, J., Tihelka, D., & Psutka, J. (2003). Automatic segmentation for Czech concatenative speech synthesis using statistical approach with boundary-specific correction. In Proceedings of the 8th European conference on speech communication and technology (EUROSPEECH 2003) (pp.\u00a0301\u2013304).","DOI":"10.21437\/Eurospeech.2003-124"},{"key":"9038_CR30","doi-asserted-by":"crossref","unstructured":"Mporas, I., Ganchev, T., & Fakotakis, N. (2008). A\u00a0hybrid architecture for automatic segmentation of speech waveforms. In Proceedings of the 2008 IEEE international conference on acoustics, speech, and signal processing (ICASSP 2008) (pp.\u00a04457\u20134460).","DOI":"10.1109\/ICASSP.2008.4518645"},{"key":"9038_CR31","doi-asserted-by":"crossref","unstructured":"Nogueira, W., Giese, A., Edler, B., & B\u00fcchner, A. (2006). Wavelet packet filter-bank for speech processing strategies in cochlear implants. In Proceedings of the IEEE international conference on acoustics, speech, and signal processing (ICASSP 2006) (Vol.\u00a05, pp.\u00a0121\u2013124).","DOI":"10.1109\/ICASSP.2006.1661227"},{"issue":"10","key":"9038_CR32","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1109\/LSP.2006.875347","volume":"13","author":"S. S. Park","year":"2006","unstructured":"Park, S. S., & Kim, N. S. (2006). Automatic speech segmentation based on boundary-type candidate selection. IEEE Signal Processing Letters, 13(10), 640\u2013643.","journal-title":"IEEE Signal Processing Letters"},{"issue":"8","key":"9038_CR33","doi-asserted-by":"crossref","first-page":"2202","DOI":"10.1109\/TASL.2007.903933","volume":"15","author":"S. S. Park","year":"2007","unstructured":"Park, S. S., & Kim, N. S. (2007). On using multiple models for automatic speech segmentation. IEEE Transactions on Audio, Speech, and Language Processing, 15(8), 2202\u20132212.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9038_CR34","doi-asserted-by":"crossref","unstructured":"Paulo, S., & Oliveira, L. C. (2003). DTW-based phonetic alignment using multiple acoustic features. In Proceedings of the 8th European conference on speech communication and technology (EUROSPEECH 2003) (pp.\u00a0309\u2013312).","DOI":"10.21437\/Eurospeech.2003-126"},{"key":"9038_CR35","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/0167-6393(96)00031-3","volume":"19","author":"S. Pauws","year":"1996","unstructured":"Pauws, S., Kamp, Y., & Willems, L. (1996). A hierarchical method of automatic speech segmentation for synthesis applications. Speech Communication, 19, 207\u2013220.","journal-title":"Speech Communication"},{"key":"9038_CR36","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/S0167-6393(98)00031-4","volume":"25","author":"B. L. Pellom","year":"1998","unstructured":"Pellom, B. L., & Hansen, J. H. L. (1998). Automatic segmentation of speech recorded in unknown noisy channel characteristics. Speech Communication, 25, 97\u2013116.","journal-title":"Speech Communication"},{"key":"9038_CR37","doi-asserted-by":"crossref","unstructured":"Petek, B., Andersen, O., & Dalsgaard, P. (1996). On the robust automatic segmentation of spontaneous speech. In Proceedings of the 4th international conference on spoken language processing (ICSLP 1996) (Vol.\u00a02, pp.\u00a0913\u2013916).","DOI":"10.1109\/ICSLP.1996.607750"},{"issue":"7","key":"9038_CR38","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1109\/97.847363","volume":"7","author":"R. Sarikaya","year":"2000","unstructured":"Sarikaya, R., & Hansen, J. H. L. (2000). High resolution speech feature parameterization for monophone-based stressed speech recognition. IEEE Signal Processing Letters, 7(7), 182\u2013185.","journal-title":"IEEE Signal Processing Letters"},{"key":"9038_CR39","doi-asserted-by":"crossref","unstructured":"Sethy, A., & Narayanan, S. (2002). Refined speech segmentation for concatenative speech synthesis. In Proceedings of the 7th international conference on spoken language processing (ICSLP 2002) (pp.\u00a0149\u2013152).","DOI":"10.21437\/ICSLP.2002-89"},{"issue":"3","key":"9038_CR40","doi-asserted-by":"crossref","first-page":"1774","DOI":"10.1121\/1.1777872","volume":"116","author":"M. D. Skowronski","year":"2004","unstructured":"Skowronski, M. D., & Harris, J. G. (2004). Exploiting independent filter bandwidth of human factor cepstral coefficients in automatic speech recognition. Journal of the Acoustical Society of America, 116(3), 1774\u20131780.","journal-title":"Journal of the Acoustical Society of America"},{"key":"9038_CR41","unstructured":"Slaney, M. (1998). Auditory toolbox, Version\u00a02 (Technical Report #1998-010). Interval Research Corporation."},{"key":"9038_CR42","doi-asserted-by":"crossref","unstructured":"Svendsen, T., & Soong, F. K. (1987). On the automatic segmentation of speech signals. In Proceedings of the 1987 IEEE international conference on acoustics, speech, and signal processing (ICASSP 1987) (pp.\u00a077\u201380).","DOI":"10.1109\/ICASSP.1987.1169628"},{"issue":"6","key":"9038_CR43","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1109\/TSA.2003.813579","volume":"11","author":"D. T. Toledano","year":"2003","unstructured":"Toledano, D. T., Gomez, L. A. H., & Grande, L. V. (2003). Automatic phonetic segmentation. IEEE Transactions on Speech and Audio Processing, 11(6), 617\u2013625.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"4","key":"9038_CR44","doi-asserted-by":"crossref","first-page":"1008","DOI":"10.1109\/78.80941","volume":"39","author":"J. P. Hemert van","year":"1991","unstructured":"van Hemert, J. P. (1991). Automatic segmentation of speech. IEEE Transactions on Signal Processing, 39(4), 1008\u20131012.","journal-title":"IEEE Transactions on Signal Processing"},{"issue":"2","key":"9038_CR45","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1109\/TIT.1967.1054010","volume":"13","author":"A. Viterbi","year":"1967","unstructured":"Viterbi, A. (1967). Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. IEEE Transactions on Information Theory, 13(2), 260\u2013269.","journal-title":"IEEE Transactions on Information Theory"},{"key":"9038_CR46","unstructured":"Wang, L., Zhao, Y., Chu, M., Zhou, J., & Cao, Z. (2004). Refining segmental boundaries for TTS database using fine contextual-dependent boundary models. In Proceedings of the 2004 IEEE international conference on acoustics, speech, and signal processing (ICASSP 2004) (Vol.\u00a01, pp.\u00a0641\u2013644)."},{"key":"9038_CR47","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1007\/978-1-4612-1894-4_25","volume-title":"Progress in speech synthesis","author":"C. W. Wightman","year":"1997","unstructured":"Wightman, C. W., & Talkin, D. T. (1997). The aligner: text-to-speech alignment using Markov models. In J. P. H. van Santen, R. W. Sproat, J. P. Olive, & J. Hirschberg (Eds.), Progress in speech synthesis (pp.\u00a0313\u2013323). Berlin: Springer."},{"key":"9038_CR48","unstructured":"Young, S., Evermann, G., Gales, M., Hain, T., Kershaw, D., Liu, X., Moore, G., Odell, J., Ollason, D., Povey, D., Valtchev, V., & Woodland, P. (2006). The HTK book (for HTK version\u00a03.4). Cambridge University, Engineering Department."},{"key":"9038_CR49","unstructured":"Ziolko, B., Manandhar, S., & Wilson, R. C. (2006). Phoneme segmentation of speech. In Proceedings of the 18th international conference on pattern recognition (ICPR 2006) (pp.\u00a0282\u2013285)."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-009-9038-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-009-9038-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-009-9038-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,26]],"date-time":"2023-05-26T09:42:02Z","timestamp":1685094122000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-009-9038-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,6]]},"references-count":49,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2008,6]]}},"alternative-id":["9038"],"URL":"https:\/\/doi.org\/10.1007\/s10772-009-9038-4","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2008,6]]}}}