{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T11:39:55Z","timestamp":1725449995190},"reference-count":44,"publisher":"Elsevier BV","issue":"3-4","license":[{"start":{"date-parts":[[2002,11,1]],"date-time":"2002-11-01T00:00:00Z","timestamp":1036108800000},"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":[[2002,11]]},"DOI":"10.1016\/s0167-6393(01)00054-1","type":"journal-article","created":{"date-parts":[[2002,10,30]],"date-time":"2002-10-30T23:54:04Z","timestamp":1036022044000},"page":"237-265","source":"Crossref","is-referenced-by-count":2,"title":["Diphone subspace mixture trajectory models for HMM complementation"],"prefix":"10.1016","volume":"38","author":[{"given":"K.","family":"Reinhard","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M.","family":"Niranjan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0167-6393(01)00054-1_BIB1","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1109\/ICASSP.1983.1172248","article-title":"Efficient coding of LPC parameters by temporal decomposition","volume":"1","author":"Atal","year":"1983","journal-title":"Internat. Conf. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(01)00054-1_BIB2","unstructured":"Blackburn, C., 1996. Articulatory methods for speech production and recognition. Ph.D. Thesis, Engineering Department, Cambridge University"},{"key":"10.1016\/S0167-6393(01)00054-1_BIB3","doi-asserted-by":"crossref","first-page":"1623","DOI":"10.21437\/Eurospeech.1995-393","article-title":"Towards improved speech recognition using a speech production model","volume":"3","author":"Blackburn","year":"1995","journal-title":"Eur. Conf. Speech Commun. Technol. (Eurospeech)"},{"key":"10.1016\/S0167-6393(01)00054-1_BIB4","doi-asserted-by":"crossref","first-page":"883","DOI":"10.21437\/Eurospeech.1995-3","article-title":"Towards increasing speech recognition error rates","volume":"2","author":"Bourlard","year":"1995","journal-title":"Eur. Conf. Speech Commun. Technol. (Eurospeech)"},{"key":"10.1016\/S0167-6393(01)00054-1_BIB5","unstructured":"Bridle, J., Deng, L., Picone, J., Richards, H., Ma, J., Kamm, T., Schuster, M., Pike, S., Regan, R., 1998. An investigation of segmental hidden dynamic models of speech coarticulation for automatic speech recognition. In: Workshop on Language Engineering, Johns Hopkins University"},{"key":"10.1016\/S0167-6393(01)00054-1_BIB6","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1016\/S0167-6393(98)00023-5","article-title":"A dynamic, feature-based approach to the interface between phonology and phonetics for speech modeling and recognition","volume":"24","author":"Deng","year":"1998","journal-title":"Speech Communication"},{"issue":"4","key":"10.1016\/S0167-6393(01)00054-1_BIB7","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1109\/89.593305","article-title":"Speaker-indepedent phonetic classification using hidden Markov models with mixture of trend functions","volume":"5","author":"Deng","year":"1997","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"4","key":"10.1016\/S0167-6393(01)00054-1_BIB8","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1109\/89.326610","article-title":"Speech recognition using hidden Markov models with polynomial regression functions as nonstationary states","volume":"2","author":"Deng","year":"1994","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/S0167-6393(01)00054-1_BIB9","first-page":"1403","article-title":"Model parameter estimation for mixture density polynomial segment models","volume":"2","author":"Fukada","year":"1997","journal-title":"Internat. Conf. Acoust. Speech Signal Process."},{"issue":"1","key":"10.1016\/S0167-6393(01)00054-1_BIB10","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1109\/TASSP.1986.1164788","article-title":"Speaker independent isolated word recognition using dynamic features of speech spectrum","volume":"34","author":"Furui","year":"1986","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(01)00054-1_BIB11","doi-asserted-by":"crossref","first-page":"1579","DOI":"10.21437\/Eurospeech.1993-354","article-title":"Segmental hidden Markov models","volume":"3","author":"Gales","year":"1993","journal-title":"Eur. Conf. Speech Commun. Technol. (Eurospeech)"},{"key":"10.1016\/S0167-6393(01)00054-1_BIB12","unstructured":"Garofolo, J., 1988. Getting started with the DARPA TIMIT CD-ROM: an acoustic phonetic continuous speech database. Technical report, National Institute of Standards and Technology (NIST)"},{"key":"10.1016\/S0167-6393(01)00054-1_BIB13","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1006\/csla.1993.1005","article-title":"Hidden Markov models with templates as non-stationary states: an application to speech recognition","volume":"2","author":"Ghitza","year":"1993","journal-title":"Comput. Speech Language"},{"key":"10.1016\/S0167-6393(01)00054-1_BIB14","doi-asserted-by":"crossref","first-page":"532","DOI":"10.1109\/ICASSP.1989.266481","article-title":"Some statistical issues in the comparison of speech recognition algorithms","volume":"1","author":"Gillick","year":"1989","journal-title":"Internat. Conf. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(01)00054-1_BIB15","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1109\/ICASSP.1993.319337","article-title":"A segmental speech model with applications to word spotting","volume":"2","author":"Gish","year":"1993","journal-title":"Internat. Conf. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(01)00054-1_BIB16","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1109\/ICSLP.1996.607155","article-title":"Parametric trajectory models for speech recognition","volume":"1","author":"Gish","year":"1996","journal-title":"Internat. Conf. Spoken Language Process."},{"key":"10.1016\/S0167-6393(01)00054-1_BIB17","doi-asserted-by":"crossref","unstructured":"Goldenthal, W., 1994. Statistical trajectory models for phonetic recognition. Ph.D. Thesis, Department of Aeronautics and Astronautics, MIT","DOI":"10.1121\/1.409413"},{"key":"10.1016\/S0167-6393(01)00054-1_BIB18","first-page":"289","article-title":"Temporal patterns (TRAPS) in ASR of noisy speech","volume":"1","author":"Hermansky","year":"1999","journal-title":"Internat. Conf. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(01)00054-1_BIB19","doi-asserted-by":"crossref","first-page":"1611","DOI":"10.21437\/Eurospeech.1995-390","article-title":"Speech recognition using a linear dynamic segmental HMM","volume":"3","author":"Holmes","year":"1995","journal-title":"Eur. Conf. Speech Commun. Technol. (Eurospeech)"},{"key":"10.1016\/S0167-6393(01)00054-1_BIB20","first-page":"1399","article-title":"Linear dynamic segmental HMMs: Variability representation and training procedure","volume":"2","author":"Holmes","year":"1997","journal-title":"Internat. Conf. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(01)00054-1_BIB21","first-page":"1017","article-title":"Unified frame and segment based models for automatic speech recognition","volume":"2","author":"Hon","year":"2000","journal-title":"Internat. Conf. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(01)00054-1_BIB22","first-page":"3369","article-title":"A diphone-based digit recognition system using neural networks","volume":"4","author":"Hosom","year":"1997","journal-title":"Internat. Conf. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(01)00054-1_BIB23","doi-asserted-by":"crossref","unstructured":"Kannan, A., Ostendorf, M., Rohlicek, J., 1992. Weight estimation for N-best rescoring. In: Proc. DARPA Speech and Natural Language Workshop, pp. 455\u2013456","DOI":"10.3115\/1075527.1075638"},{"key":"10.1016\/S0167-6393(01)00054-1_BIB24","unstructured":"Lamel, L., Kassel, R., Seneff, S., 1986. Speech database development: design and analysis of the acoustic-phonetic corpus. In: Proc. Speech Recognition Workshop (DARPA), pp. 100\u2013109"},{"issue":"2","key":"10.1016\/S0167-6393(01)00054-1_BIB25","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","article-title":"Least squares quantization in PCM","volume":"28","author":"Lloyd","year":"1982","journal-title":"IEEE Trans. Inf. Theory"},{"key":"10.1016\/S0167-6393(01)00054-1_BIB26","unstructured":"Marcus, S., van Lieshout, R., 1984. Temporal decomposition of speech. Annual Progress Report, IPO, Eindhoven, pp. 25\u201331"},{"key":"10.1016\/S0167-6393(01)00054-1_BIB27","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1109\/ICASSP.1988.196660","article-title":"Stochastic model of diphone-like segments based on trajectory concepts","volume":"1","author":"Marteau","year":"1988","journal-title":"Internat. Conf. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(01)00054-1_BIB28","first-page":"1943","article-title":"Stochastic perceptual auditory-events-based models for speech recognition","volume":"4","author":"Morgan","year":"1994","journal-title":"Internat. Conf. Spoken Language Process."},{"key":"10.1016\/S0167-6393(01)00054-1_BIB29","first-page":"397","article-title":"Stochastic perceptual models of speech","volume":"1","author":"Morgan","year":"1995","journal-title":"Inernat. Conf. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(01)00054-1_BIB30","first-page":"71","article-title":"On modelling the dynamics of speech patterns","volume":"1","author":"Niranjan","year":"1987","journal-title":"Eur. Conf. Speech Technol."},{"key":"10.1016\/S0167-6393(01)00054-1_BIB31","series-title":"Subspace Methods of Pattern Recognition","author":"Oja","year":"1983"},{"key":"10.1016\/S0167-6393(01)00054-1_BIB32","series-title":"Speech Communication \u2013 Human and Machine","author":"O'Shaughnessy","year":"2000"},{"issue":"12","key":"10.1016\/S0167-6393(01)00054-1_BIB33","doi-asserted-by":"crossref","first-page":"1857","DOI":"10.1109\/29.45533","article-title":"A stochastic segment model for phoneme-based continuous speech recognition","volume":"37","author":"Ostendorf","year":"1989","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(01)00054-1_BIB34","doi-asserted-by":"crossref","unstructured":"Ostendorf, M., Kannan, A., Austin, S., Kimball, O., Schwartz, R., Rohlicek, J., 1991. Integration of diverse recognition methodologies through reevaluation of N-best sentence hypotheses. In: Proc. DARPA Speech and Natural Language Workshop, pp. 83\u201387","DOI":"10.3115\/112405.112416"},{"issue":"5","key":"10.1016\/S0167-6393(01)00054-1_BIB35","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1109\/89.536930","article-title":"From HMM's to segment models: A unified view of stochastic modeling for speech recognition","volume":"4","author":"Ostendorf","year":"1996","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/S0167-6393(01)00054-1_BIB36","first-page":"109","article-title":"Initial evaluation of hidden dynamic models on conversational speech","volume":"1","author":"Picone","year":"1999","journal-title":"Internat. Conf. Acoust. Speech Signal Process."},{"issue":"1","key":"10.1016\/S0167-6393(01)00054-1_BIB37","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/S0167-6393(98)00067-3","article-title":"Parametric subspace modeling of speech transitions","volume":"27","author":"Reinhard","year":"1999","journal-title":"Speech Communication"},{"key":"10.1016\/S0167-6393(01)00054-1_BIB38","first-page":"357","article-title":"The HDM: A segmental hidden dynamic model of coarticulation","volume":"1","author":"Richards","year":"1999","journal-title":"Internat. Conf. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(01)00054-1_BIB39","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1109\/ICASSP.1993.319351","article-title":"A segmental HMM for speech pattern modelling","volume":"2","author":"Russell","year":"1993","journal-title":"Internat. Conf. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(01)00054-1_BIB40","first-page":"751","article-title":"Markov processes on curves for automatic speech recognition","volume":"11","author":"Saul","year":"1998","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/S0167-6393(01)00054-1_BIB41","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1109\/ICASSP.1990.115542","article-title":"The N-best algorithm: An efficient and exact procedure for finding the N most likely sentence hypotheses","volume":"1","author":"Schwartz","year":"1990","journal-title":"Internat. Conf. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(01)00054-1_BIB42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ICASSP.1976.1170100","article-title":"New uses for the N-best sentence hypotheses within the BYBLOS speech recognition system","volume":"1","author":"Schwartz","year":"1992","journal-title":"Internat. Conf. Acoust. Speech Signal Process."},{"issue":"2","key":"10.1016\/S0167-6393(01)00054-1_BIB43","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1109\/TIT.1967.1054010","article-title":"Error bounds for convolutional codes and an asymptotically optimum decoding algorithm","volume":"IT-13","author":"Viterbi","year":"1967","journal-title":"IEEE Trans. Inf. Theory"},{"key":"10.1016\/S0167-6393(01)00054-1_BIB44","doi-asserted-by":"crossref","unstructured":"Young, S., Odell, J., Woodland, P., 1994. Tree-based state tying for high accuracy acoustic modeling. In: ARPA Workshop on Human Language Technology, pp. 307\u2013312","DOI":"10.3115\/1075812.1075885"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639301000541?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639301000541?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2023,4,6]],"date-time":"2023-04-06T23:41:59Z","timestamp":1680824519000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639301000541"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2002,11]]},"references-count":44,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2002,11]]}},"alternative-id":["S0167639301000541"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6393(01)00054-1","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[2002,11]]}}}