{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T10:52:40Z","timestamp":1774003960257,"version":"3.50.1"},"reference-count":36,"publisher":"Elsevier BV","issue":"4","license":[{"start":{"date-parts":[[2003,6,1]],"date-time":"2003-06-01T00:00:00Z","timestamp":1054425600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Speech Communication"],"published-print":{"date-parts":[[2003,6]]},"DOI":"10.1016\/s0167-6393(02)00131-0","type":"journal-article","created":{"date-parts":[[2003,5,13]],"date-time":"2003-05-13T04:46:45Z","timestamp":1052801205000},"page":"503-515","source":"Crossref","is-referenced-by-count":35,"title":["Phonetic alignment: speech synthesis-based vs. Viterbi-based"],"prefix":"10.1016","volume":"40","author":[{"given":"F.","family":"Malfr\u00e8re","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"O.","family":"Deroo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"T.","family":"Dutoit","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C.","family":"Ris","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0167-6393(02)00131-0_BIB1","series-title":"Proceedings of the International Conference on Acoustics Speech and Signal Processing","first-page":"41","article-title":"Performance of the IBM large vocabulary continuous speech recognition system on the ARPA Wall Street Journal task","author":"Bahl","year":"1995"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB2","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1109\/TASSP.1975.1162650","article-title":"The Dragon system\u2013\u2013an overwiew","author":"Baker","year":"1975","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(02)00131-0_BIB3","first-page":"1","article-title":"An inequally and associated maximization technique in statistical estimation of probabilistic functions of Markov processes","volume":"3","author":"Baum","year":"1972","journal-title":"Inequalities"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB4","series-title":"Connectionist Speech Recognition\u2013\u2013A Hybrid Approach","author":"Bourlard","year":"1994"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB5","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1016\/0167-6393(93)90083-W","article-title":"Automatic segmentation and labeling of speech based on hidden Markov models","author":"Brugnara","year":"1993","journal-title":"Speech Commun."},{"key":"10.1016\/S0167-6393(02)00131-0_BIB6","doi-asserted-by":"crossref","unstructured":"Carr\u00e9, R., Descoudt, R., Esk\u00e9nazi, M., Mariani, J., Rossi, M., 1984. The French language database: defining, planning and recording a large database. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing","DOI":"10.1109\/ICASSP.1984.1172715"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB7","series-title":"Proceedings of the European Conference on Speech Communication and Technology","first-page":"693","article-title":"A preliminary statistical evaluation of manual and automatic segmentation","author":"Cosi","year":"1991"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB8","series-title":"Proceedings of the European Conference on Signal Processing (EUSIPCO\u201998)","first-page":"1161","article-title":"Comparison of two different alignment systems: speech synthesis vs. hybrid HMM\/ANN","author":"Deroo","year":"1998"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB9","series-title":"Proceedings of the European Conference on Speech Communication and Technology","first-page":"843","article-title":"Automatic detection and correction of pronunciation errors for foreign language learners: the DEMOSTHENES application","author":"Deville","year":"1999"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB10","series-title":"Proceedings of the European Conference on Speech Communication and Technology","first-page":"1947","article-title":"Context independent and context dependent hybrid HMM\/ANN systems for vocabulary independent tasks","author":"Dupont","year":"1997"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB11","series-title":"International Conference on Speech and Language Processing","first-page":"1393","article-title":"The MBROLA project: towards a set of high quality speech synthesizers free for use for non-commercial purposes","author":"Dutoit","year":"1996"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB12","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1006\/csla.1994.1010","article-title":"Context-dependent connectionist probability estimation in a hybrid hidden Markov model-neural net speech recognition system","author":"Franco","year":"1994","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/S0167-6393(02)00131-0_BIB13","doi-asserted-by":"crossref","DOI":"10.1121\/1.399423","article-title":"Perceptual linear predictive analysis of speech","author":"Hermansky","year":"1990","journal-title":"J. Acoust. Soc. Am"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB14","series-title":"Spoken Language Systems Technology Workshop","first-page":"170","article-title":"The 1994 ABBOT hybrid connectionist-HMM large vocabulary recognition system","author":"Hochberg","year":"1995"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB15","series-title":"Improvements in Speech Synthesis","first-page":"331","article-title":"Automatic speech segmentation based on DTW with the application of the Czech TTS system","author":"Horak","year":"2001"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB16","series-title":"Proceedings of the International Conference on Acoustics, Speech and Signal Processing","first-page":"373","article-title":"Unit selection in a concatenative speech synthesis system using large speech database","author":"Hunt","year":"1996"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB17","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1109\/PROC.1976.10159","article-title":"Continuous speech recognition by statistical methods","author":"Jelinek","year":"1976","journal-title":"Proc. IEEE"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB18","series-title":"Proceedings of the International Conference on Acoustics Speech and Signal Processing","first-page":"765","article-title":"On the use of bandpass liftering in speech recognition","author":"Juang","year":"1986"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB19","doi-asserted-by":"crossref","unstructured":"Koehler, J., Morgan, N., Hermansky, H., Hirsch, H.G., Tong, G., 1994. INTEGRATING RASTA-PLP INTO SPEECH RECOGNITION. In: Proceedings of the International Conference on Acoustics Speech and Signal Processing. Adelaide, Australia, April, pp. I-421\u2013I-424","DOI":"10.1109\/ICASSP.1994.389266"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB20","series-title":"Proceedings of the European Conference on Speech Communication and Technology","first-page":"505","article-title":"BREF, a large vocabulary spoken corpus for French","author":"Lamel","year":"1991"},{"issue":"1","key":"10.1016\/S0167-6393(02)00131-0_BIB21","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1109\/89.650310","article-title":"A frequency warping approach to speaker normalization","volume":"6","author":"Lee","year":"1998","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/S0167-6393(02)00131-0_BIB22","doi-asserted-by":"crossref","unstructured":"Lenzo, K., Black, A.W., 2000. Diphone collection and synthesis. In: Proceedings of the International Conference on Speech and Language Processing. Beijing, China","DOI":"10.21437\/ICSLP.2000-537"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB23","series-title":"Proceedings of the International Conference on Acoustics, Speech and Signal Processing","first-page":"2.7.1","article-title":"A procedure for automatic alignment of phonetic transcriptions with continuous speech","author":"Leung","year":"1984"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB24","series-title":"Proceedings International Conference on Acoustics, Speech and Signal Processing","first-page":"473","article-title":"Automatic segmentation and labeling of speech","author":"Ljolje","year":"1991"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB25","series-title":"Proceedings of the European Conference on Speech Communication and Technology","first-page":"2631","article-title":"High-quality speech synthesis for phonetic speech segmentation","author":"Malfr\u00e8re","year":"1997"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB26","doi-asserted-by":"crossref","unstructured":"Myers, C.S., Rabiner, L.R., 1981. A level building dynamic time warping algorithm for connected word recognition. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing","DOI":"10.1109\/ICASSP.1981.1171123"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB27","series-title":"DARPA Speech and Language Workshop","article-title":"The design for the Wall Street Journal-based CSR Corpus","author":"Paul","year":"1992"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB28","series-title":"Fundamentals of Speech Recognition","author":"Rabiner","year":"1993"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB29","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1109\/72.279192","article-title":"An application of recurrent nets to phone probability estimation","author":"Robinson","year":"1994","journal-title":"Proc. IEEE Trans. Neural Network"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB30","first-page":"257","article-title":"A reccurent error propagation network speech recognition system","author":"Robinson","year":"1991","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/S0167-6393(02)00131-0_BIB31","series-title":"Proceedings of the International Conference on Acoustics Speech Signal Processing","first-page":"69","article-title":"The ARM continuous speech recognition system","author":"Russell","year":"1990"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB32","series-title":"Proceedings of Second ESCA\/IEEE Workshop on Speech Synthesis","first-page":"89","article-title":"The aligner: text-to-speech alignment using Markov models and a pronunciation dictionary","author":"Talkin","year":"1996"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB33","unstructured":"Traber, C., 1995. SVOX: The Implementation of a Text-to-Speech System for German, PhD Thesis, ETH Zurich"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB34","doi-asserted-by":"crossref","unstructured":"Van Coile, B., Van Tichelen, L., Vostermans, A., Wang, J.W., Staessen, M., 1994. PROTRAN: A prosody transplantation tool for text-to-speech applications. In: Proceedings of ICSLP\u201994","DOI":"10.21437\/ICSLP.1994-108"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB35","series-title":"Proceedings of the International Conference on Acoustics, Speech and Signal Processing","first-page":"73","article-title":"The 1994 HTK large vocabulary speech recognition system","author":"Woodland","year":"1995"},{"key":"10.1016\/S0167-6393(02)00131-0_BIB36","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1016\/0167-6393(90)90010-7","article-title":"Speech Database Development: TIMIT and Beyond","author":"Zue","year":"1990","journal-title":"Speech Commun."}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639302001310?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639302001310?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2023,4,24]],"date-time":"2023-04-24T17:45:44Z","timestamp":1682358344000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639302001310"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,6]]},"references-count":36,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2003,6]]}},"alternative-id":["S0167639302001310"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6393(02)00131-0","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[2003,6]]}}}