{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,5,5]],"date-time":"2024-05-05T20:32:55Z","timestamp":1714941175363},"reference-count":97,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[1996,1,1]],"date-time":"1996-01-01T00:00:00Z","timestamp":820454400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Speech Audio Process."],"published-print":{"date-parts":[[1996]]},"DOI":"10.1109\/89.536930","type":"journal-article","created":{"date-parts":[[2002,8,24]],"date-time":"2002-08-24T19:31:03Z","timestamp":1030217463000},"page":"360-378","source":"Crossref","is-referenced-by-count":334,"title":["From HMM's to segment models: a unified view of stochastic modeling for speech recognition"],"prefix":"10.1109","volume":"4","author":[{"given":"M.","family":"Ostendorf","sequence":"first","affiliation":[]},{"given":"V.V.","family":"Digalakis","sequence":"additional","affiliation":[]},{"given":"O.A.","family":"Kimball","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266485"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1991.150378"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075638"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075858"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075906"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/112405.112416"},{"key":"ref37","author":"gales","year":"1993","journal-title":"The theory of segmental hidden Markov models"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177697196"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1986.tb00368.x"},{"key":"ref34","first-page":"1","article-title":"maximum likelihood estimation from incomplete data","volume":"39","author":"dempster","year":"1977","journal-title":"J Royal Statist Soc B"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/78.175733"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/29.45533"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479663"},{"key":"ref20","first-page":"17","article-title":"secondary processing using speech segments for an hmm word spotting system","volume":"i","author":"gish","year":"1992","journal-title":"Proc Int Conf Spoken Language"},{"key":"ref22","article-title":"continuous word recognition based on the stochastic segment model","author":"ostendorf","year":"1992","journal-title":"Proc DARPA Workshop CSR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1988.196528"},{"key":"ref24","author":"fong","year":"1993","journal-title":"Statistical models of duration for synthesis and recognition"},{"key":"ref23","first-page":"9","article-title":"stochastic segment modeling for csr: the bu wsj benchmark system","author":"ostendorf","year":"1994","journal-title":"Proc ARPA Workshop Spoken Language Technol"},{"key":"ref26","article-title":"segmental duration and speech timing","author":"van santen","year":"0","journal-title":"Computing Prosody"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1988.196629"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225855"},{"key":"ref51","first-page":"291","article-title":"non-linear time alignment in stochastic trajectory models for speech recognition","author":"afify","year":"1994","journal-title":"Proc Int Conf Spoken Language Processing"},{"key":"ref59","first-page":"2167","article-title":"speech recognition using dynamically defined speech units","volume":"4","author":"deng","year":"1994","journal-title":"Proc Int Conf Spoken Language Processing"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/0165-1684(94)90089-2"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1994.389358"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319337"},{"key":"ref55","first-page":"139","article-title":"the 1994 bu nab news benchmark system","volume":"1995","author":"ostendorf","year":"0","journal-title":"Proc ARPA Workshop Spoken Language Technol"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/1075671.1075694"},{"key":"ref53","doi-asserted-by":"crossref","first-page":"289","DOI":"10.21437\/Eurospeech.1993-92","article-title":"modeling spectral dynamics for vowel classification","author":"goldenthal","year":"1993","journal-title":"Proc Euro Conf Speech Commun Technology"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3115\/1075434.1075491"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/0885-2308(90)90002-N"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0885-2308(86)80009-2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168477"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.21236\/ADA188529","author":"brown","year":"1987","journal-title":"The acoustic modeling problem in automatic speech recognition"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1987.1169614"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319351"},{"key":"ref49","author":"breiman","year":"1984","journal-title":"Classification and Regression Trees"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/29.103057"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1579","DOI":"10.21437\/Eurospeech.1993-354","article-title":"segmental hmm's for speech recognition","author":"gales","year":"1993","journal-title":"Proc Euro Conf Speech Commun Technol"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075566"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1991.150308"},{"key":"ref48","first-page":"537","article-title":"genones: optimizing the degree of tying in a large vocabulary hmm-based speech recognizer","volume":"i","author":"digalakis","year":"1994","journal-title":"Proc Int Conf Acoust Speech Signal Processing"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"2207","DOI":"10.21437\/Eurospeech.1993-495","article-title":"the htk tied-state continuous speech recognizer","author":"woodland","year":"1993","journal-title":"Proc Euro Conf Speech Commun Technol"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/78.139267"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075568"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/89.294362"},{"key":"ref43","author":"ross","year":"1995","journal-title":"Computational models of intonation for speech synthesis"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115744"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115742"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115740"},{"key":"ref70","doi-asserted-by":"crossref","first-page":"807","DOI":"10.21437\/Eurospeech.1993-143","article-title":"linear and nonlinear prediction for speech recognition with hidden markov models","author":"saerens","year":"1993","journal-title":"Proc Euro Conf Speech Commun Technology"},{"key":"ref76","first-page":"1623","article-title":"toward improved speech recognition using a speech production model","author":"blackburn","year":"1995","journal-title":"Proc Euro Conf Speech Commun Technol"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(94)90027-2"},{"key":"ref74","first-page":"1341","article-title":"neural predictive hidden markov model","author":"tsuboka","year":"1990","journal-title":"Proc Int Conf Spoken Language Processing"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.2307\/2288473"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075885"},{"key":"ref79","author":"kimball","year":"1994","journal-title":"Segment modeling alternatives for continuous speech recognition"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319273"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1985.1164727"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1982.1171633"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1995.0004"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225860"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319274"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/89.242489"},{"key":"ref67","article-title":"an articulatory-like speech production model with controlled use of prior knowledge","author":"bakis","year":"1993","journal-title":"Frontiers in Speech Processing Robust Speech Recognition"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479647"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/89.759037"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1983.4767370"},{"key":"ref95","first-page":"1871","article-title":"statistical trajectory models for phonetic recognition","author":"goldenthal","year":"1994","journal-title":"Proc Int Conf Spoken Language Processing"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/89.260358"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.226048"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225834"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075570"},{"key":"ref90","first-page":"931","article-title":"speech recognition using stochastic explicit-segment modeling","volume":"2","author":"leung","year":"1991","journal-title":"Proc Euro Conf Speech Commun Technology"},{"key":"ref96","first-page":"835","article-title":"empirical acquisition of language models for speech recognition","author":"mccandless","year":"1994","journal-title":"Proc Int Conf Spoken Language Processing"},{"key":"ref97","first-page":"831","article-title":"toward better language models for spontaneous speech","author":"suhn","year":"1994","journal-title":"Proc Int Conf Spoken Language Processing"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1987.1165057"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266447"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1991.150333"},{"key":"ref13","author":"digalakis","year":"1992","journal-title":"Segment-based stochastic models of spectral dynamics for continuous speech recognition"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319303"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/89.326610"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1993.1005"},{"key":"ref82","first-page":"1611","article-title":"speech recognition using a linear dynamic segmental hmm","author":"holmes","year":"1995","journal-title":"Proc Euro Conf Speech Commun Technol"},{"key":"ref17","first-page":"532","article-title":"a unified way in incorporating segmental feature and segmental model into hmm","author":"he","year":"1995","journal-title":"Proc Int Conf Acoust Speech Signal Processing"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.1991.186590"},{"key":"ref18","article-title":"recognition of intonation labels using a dynamical system model","author":"ostendorf","year":"0","journal-title":"Computing Prosody"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.4.461"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/78.80762"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/34.62605"},{"key":"ref80","first-page":"57","article-title":"stochastic trajectory modeling for speech recognition","volume":"i","author":"gong","year":"1994","journal-title":"Proc Int Conf Acoust Speech Signal Processing"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115865"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/5.381844"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/89.260359"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/89.326607"},{"key":"ref88","first-page":"170","article-title":"the 1994 abbot hybrid connectionist-hmm large-vocabulary recognition system","author":"hochberg","year":"1995","journal-title":"Proc ARPA Workship Spoken Language Technol"}],"container-title":["IEEE Transactions on Speech and Audio Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx4\/89\/11518\/00536930.pdf?arnumber=536930","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,5]],"date-time":"2024-01-05T18:13:51Z","timestamp":1704478431000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/536930\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1996]]},"references-count":97,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/89.536930","relation":{},"ISSN":["1063-6676"],"issn-type":[{"value":"1063-6676","type":"print"}],"subject":[],"published":{"date-parts":[[1996]]}}}