{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T06:02:01Z","timestamp":1778824921584,"version":"3.51.4"},"reference-count":42,"publisher":"Elsevier BV","issue":"2","license":[{"start":{"date-parts":[[1996,8,1]],"date-time":"1996-08-01T00:00:00Z","timestamp":838857600000},"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":[[1996,8]]},"DOI":"10.1016\/0167-6393(96)00033-7","type":"journal-article","created":{"date-parts":[[2002,7,25]],"date-time":"2002-07-25T20:26:49Z","timestamp":1027628809000},"page":"161-176","source":"Crossref","is-referenced-by-count":17,"title":["Modelling of phone duration (using the TIMIT database) and its potential benefit for ASR"],"prefix":"10.1016","volume":"19","author":[{"given":"Louis C.W.","family":"Pols","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Louis F.M.","family":"ten Bosch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"No. 3","key":"10.1016\/0167-6393(96)00033-7_NEWBIB1","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1016\/0167-6393(96)00003-9","article-title":"Towards increasing speech recognition error rates","volume":"Vol. 18","author":"Bourlard","year":"1996","journal-title":"Speech Communication"},{"issue":"No. 4","key":"10.1016\/0167-6393(96)00033-7_NEWBIB2","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","volume":"Vol. 12","author":"Brugnara","year":"1993","journal-title":"Speech Communication"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB3","first-page":"827","article-title":"Sex, dialects, and reduction","volume":"Vol. 1","author":"Byrd","year":"1992"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB4","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1159\/000259312","article-title":"Vowel length variation as a function of the voicing of the consonant environment","volume":"Vol. 22","author":"Chen","year":"1970","journal-title":"Phonetica"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB5","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1121\/1.388251","article-title":"Segmental durations in connected-speech signals: Preliminary results","volume":"Vol. 72","author":"Crystal","year":"1982","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB6","doi-asserted-by":"crossref","first-page":"1553","DOI":"10.1121\/1.395911","article-title":"Segmental durations in connected-speech signals: Current results","volume":"Vol. 83","author":"Crystal","year":"1988","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB7","doi-asserted-by":"crossref","first-page":"1574","DOI":"10.1121\/1.395912","article-title":"Segmental durations in connected-speech signals: Syllabic stress","volume":"Vol. 83","author":"Crystal","year":"1988","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB8","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1121\/1.399955","article-title":"Articulation rate and the duration of syllables and stress groups in connected speech","volume":"Vol. 88","author":"Crystal","year":"1990","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB9","article-title":"Timing in talking. Tempo variation in production and perception","author":"Eefting","year":"1991"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB10","series-title":"The DARPA TIMIT acoustic-phonetic continuous speech corpus CDROM","author":"Garofolo","year":"1993"},{"issue":"Nos. 1\u20132","key":"10.1016\/0167-6393(96)00033-7_NEWBIB11","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/0167-6393(94)90038-8","article-title":"Speaker-independent continuous speech dictation","volume":"Vol. 15","author":"Gauvain","year":"1994","journal-title":"Speech Communication"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB12","first-page":"323","article-title":"Constraining the duration variance in HMM-based connected-speech recognition","volume":"Vol. 1","author":"Hochberg","year":"1993"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB13","first-page":"311","article-title":"Using relative duration in large vocabulary speech recognition","volume":"Vol. 1","author":"Jones","year":"1993"},{"issue":"No. 2","key":"10.1016\/0167-6393(96)00033-7_NEWBIB14","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/0167-6393(94)90004-3","article-title":"Phonetic analyses of word and segment variation using the TIMIT corpus of American English","volume":"Vol. 14","author":"Keating","year":"1994","journal-title":"Speech Communication"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB15","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1121\/1.395275","article-title":"Review of text-to-speech conversion for English","volume":"Vol. 82","author":"Klatt","year":"1987","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB16","first-page":"23","article-title":"Identifying non-linguistic speech features","volume":"Vol. 1","author":"Lamel","year":"1993"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB17","first-page":"121","article-title":"High performance speaker-independent phone recognition using CDHMM","volume":"Vol. 1","author":"Lamel","year":"1993"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB18","series-title":"Proc. DARPA Speech Recognition Workshop","first-page":"100","article-title":"Speech database development: Design and analysis of the acoustic-phonetic corpus","author":"Lamel","year":"1986"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB19","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.1109\/29.46546","article-title":"Speaker-independent phone recognition using Hidden Markov Models","volume":"Vol. ASSP-37","author":"Lee","year":"1989","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB20","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/S0885-2308(86)80009-2","article-title":"Continuously variable duration hidden Markov models for automatic speech recognition","volume":"Vol. 1","author":"Levinson","year":"1986","journal-title":"Computer Speech and Language"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB21","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1006\/csla.1994.1006","article-title":"High accuracy phone recognition using context clustering and quasi-triphone models","volume":"Vol. 8","author":"Ljolje","year":"1994","journal-title":"Computer Speech and Language"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB22","series-title":"Proc. Internat. Conf. Acoust. Speech Signal Process.-91","first-page":"473","article-title":"Automatic segmentation and labeling of speech","author":"Ljolje","year":"1991"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB23","article-title":"Production and perception of vowel duration","author":"Nooteboom","year":"1970"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB24","doi-asserted-by":"crossref","first-page":"1235","DOI":"10.1121\/1.1914393","article-title":"The effect of position in utterance on speech segment duration in English","volume":"Vol. 54","author":"Oller","year":"1973","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB25","series-title":"Proc. ICSLP'90","first-page":"24.3.1, 2434","article-title":"Speech corpora and performance assessment in the DARPA SLS program","author":"Pallett","year":"1990"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB26","series-title":"Proc. ARPA Spoken Language Systems Technology Workshop","first-page":"5","article-title":"1994 Benchmark tests for the ARPA Spoken Language Program","author":"Pallett","year":"1995"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB27","doi-asserted-by":"crossref","first-page":"693","DOI":"10.1121\/1.1908183","article-title":"Duration of syllable nuclei in English","volume":"Vol. 32","author":"Peterson","year":"1960","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB28","article-title":"Several improvements to a recurrent error propagation network phone recognition system","author":"Robinson","year":"1991","journal-title":"Technical report, Cambridge Univ., CUED\/F-INFENG\/TR.82"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB29","series-title":"Proc. Internat. Conf. Acoust. Speech Signal Process. -95","first-page":"201","article-title":"Analysis of acoustic-phonetic variations in fluent speech using TIMIT","author":"Sun","year":"1995"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB30","doi-asserted-by":"crossref","first-page":"434","DOI":"10.1121\/1.380688","article-title":"Vowel duration in American English","volume":"Vol. 58","author":"Umeda","year":"1975","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB31","series-title":"Analysis and Synthesis of Speech. Strategic Research towards high-quality Text-to-speech Generation","year":"1993"},{"issue":"No. 6","key":"10.1016\/0167-6393(96)00033-7_NEWBIB32","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1016\/0167-6393(92)90027-5","article-title":"Contextual effects on vowel duration","volume":"Vol. 11","author":"Van Santen","year":"1992","journal-title":"Speech Communication"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB33","series-title":"Studies in Language and Language Use 3","article-title":"Spectro-temporal features of vowel segments","author":"Van Son","year":"1993"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB34","first-page":"1397","article-title":"Fast automatic segmentation and labeling: Results on TIMIT and EUROM0","volume":"Vol. 2","author":"Vorstermans","year":"1995"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB35","first-page":"111","article-title":"Durationally constrained training of HMM without explicit state durational pdf","volume":"Vol. 18","author":"Wang","year":"1994"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB36","series-title":"Speech Recognition and Coding. New Advances and Trends","first-page":"128","article-title":"Durational modelling in HMM-based speech recognition: Towards a justified measure","author":"Wang","year":"1995"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB37","article-title":"Duration modelling in HMM-based speech recognition","author":"Wang","year":"1996"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB38","first-page":"2207","article-title":"The HTK tied-state continuous speech recogniser","volume":"Vol. 3","author":"Woodland","year":"1993"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB39","author":"Young","year":"1992"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB40","first-page":"2203","article-title":"The use of state tying in continuous speech recognition","volume":"Vol. 3","author":"Young","year":"1993"},{"key":"10.1016\/0167-6393(96)00033-7_NEWBIB41","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1006\/csla.1994.1019","article-title":"State clustering in hidden Markov model-based continuous speech recognition","volume":"Vol. 8","author":"Young","year":"1994","journal-title":"Computer Speech and Language"},{"issue":"No. 4","key":"10.1016\/0167-6393(96)00033-7_NEWBIB42","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1016\/0167-6393(90)90010-7","article-title":"Speech database development at MIT: TIMIT and beyond","volume":"Vol. 9","author":"Zue","year":"1990","journal-title":"Speech Communication"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:0167639396000337?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:0167639396000337?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,4,16]],"date-time":"2019-04-16T19:50:45Z","timestamp":1555444245000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/0167639396000337"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1996,8]]},"references-count":42,"journal-issue":{"issue":"2","published-print":{"date-parts":[[1996,8]]}},"alternative-id":["0167639396000337"],"URL":"https:\/\/doi.org\/10.1016\/0167-6393(96)00033-7","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[1996,8]]}}}