{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,4,15]],"date-time":"2023-04-15T22:40:01Z","timestamp":1681598401957},"reference-count":43,"publisher":"Elsevier BV","issue":"1","license":[{"start":{"date-parts":[[1998,4,1]],"date-time":"1998-04-01T00:00:00Z","timestamp":891388800000},"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":[[1998,4]]},"DOI":"10.1016\/s0167-6393(97)00064-2","type":"journal-article","created":{"date-parts":[[2002,7,26]],"date-time":"2002-07-26T00:25:33Z","timestamp":1027643133000},"page":"51-72","source":"Crossref","is-referenced-by-count":4,"title":["Assessing the importance of the segmentation probability in segment-based speech recognition"],"prefix":"10.1016","volume":"24","author":[{"given":"J.","family":"Verhasselt","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"I.","family":"Illina","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J.-P.","family":"Martens","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Y.","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J.-P.","family":"Haton","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0167-6393(97)00064-2_BIB1","doi-asserted-by":"crossref","unstructured":"Afify, M., Gong, Y., Haton, J.-P., 1995. Stochastic trajectory model for speech recognition: an extension to modeling time correlation. In: Proc. Eurospeech, Vol. 1, pp. 515\u2013518.","DOI":"10.21437\/Eurospeech.1995-137"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB2","doi-asserted-by":"crossref","unstructured":"Austin, S., Zavaliagkos, G., Makhoul, J., Schwartz, R., 1992. Speech recognition using segmental neural nets. In: Proc. Internat. Conf. Acoust. Speech Signal Process., Vol. 1, pp. 625\u2013628.","DOI":"10.21236\/ADA460342"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB3","doi-asserted-by":"crossref","unstructured":"Bourlard, H., Morgan, N., 1994. Connectionist Speech Recognition: A Hybrid Approach. Kluwer Academic Publishers, Dordrecht.","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB4","unstructured":"Cerisara, C., Gong, Y., Haton, J.-P., 1996. Reconnaissance de la parole continue par le mod\u00e8le STM polyn\u00f4mial. Actes des 21-\u00e8mes Journ\u00e9es d'\u00c9tudes sur la Parole, pp. 317\u2013320."},{"key":"10.1016\/S0167-6393(97)00064-2_BIB5","doi-asserted-by":"crossref","unstructured":"Chang, J., Glass, J., 1997. Segmentation and modeling in segment-based recognition. In: Proc. Eurospeech, Vol. 3, pp. 1199\u20131202.","DOI":"10.21437\/Eurospeech.1997-23"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB6","doi-asserted-by":"crossref","unstructured":"Flammia, G., Dalsgaard, P., Andersen, O., Lindberg, B., 1992. Segment based variable frame rate speech analysis and recognition using a spectral variation function. In: Proc. ICSLP, pp. 983\u2013986.","DOI":"10.21437\/ICSLP.1992-306"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB7","doi-asserted-by":"crossref","unstructured":"Glass, J., Chang, J., McCandless, M., 1996. A probabilistic framework for feature-based speech recognition. In: Proc. ICSLP, Vol. 4, pp. 2277\u20132280.","DOI":"10.1109\/ICSLP.1996.607261"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB8","doi-asserted-by":"crossref","unstructured":"Goldenthal, W., 1994. Statistical trajectory models for phonetic recognition. PhD Thesis, Laboratory for Computer Science MIT.","DOI":"10.1121\/1.409413"},{"issue":"1","key":"10.1016\/S0167-6393(97)00064-2_BIB9","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1109\/89.554267","article-title":"Stochastic trajectory modeling and sentence searching for continuous speech recognition","volume":"5","author":"Gong","year":"1997","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/S0167-6393(97)00064-2_BIB10","doi-asserted-by":"crossref","unstructured":"Gong, Y., Haton, J.-P., 1992. DTW-based phonetic labeling using explicit phoneme duration constraints. In: Proc. ICSLP, Vol. 2, pp. 863\u2013866.","DOI":"10.21437\/ICSLP.1992-259"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB11","doi-asserted-by":"crossref","unstructured":"Gong, Y., Haton, J.-P., 1993. Iterative transformation and alignment for speech labeling. In: Proc. Eurospeech, Vol. 3, pp. 1759\u20131762.","DOI":"10.21437\/Eurospeech.1993-179"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB12","unstructured":"Gong, Y., Haton, J.-P., 1994. Stochastic trajectory modeling for speech recognition. In: Proc. Internat. Conf. Acoust. Speech Signal Process., Vol. 1, pp. 57\u201360."},{"key":"10.1016\/S0167-6393(97)00064-2_BIB13","doi-asserted-by":"crossref","unstructured":"Gong, Y., Illina, I., Haton, J.-P., 1996. Modeling long term variability information in mixture stochastic trajectory framework. In: Proc. ICSLP, Vol. 1, pp. 334\u2013337.","DOI":"10.21437\/ICSLP.1996-109"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB14","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/BF00417783","article-title":"Multilayer perceptrons combination applied to handwritten character recognition","volume":"3","author":"Gosselin","year":"1996","journal-title":"Neural Process. Lett."},{"issue":"4","key":"10.1016\/S0167-6393(97)00064-2_BIB15","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1016\/S0893-6080(96)00098-6","article-title":"Optimal linear combinations of neural networks","volume":"10","author":"Hashem","year":"1997","journal-title":"Neural Networks"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB16","doi-asserted-by":"crossref","unstructured":"Illina, I., Gong, Y., 1996. Stochastic trajectory model with state-mixture for continuous speech recognition. In: Proc. ICSLP, Vol. 1, pp. 342\u2013345.","DOI":"10.1109\/ICSLP.1996.607124"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB17","unstructured":"Katke, W., 1985. Learning language using a pattern recognition approach. The AI Magazine, 64\u201373."},{"key":"10.1016\/S0167-6393(97)00064-2_BIB18","unstructured":"Kimball, O., 1995. Segment modeling alternatives for continuous speech recognition. PhD Thesis, Boston University College of Engineering."},{"key":"10.1016\/S0167-6393(97)00064-2_BIB19","doi-asserted-by":"crossref","unstructured":"Lamel, L., 1988. Formalizing knowledge used in spectrogram reading: Acoustic and perceptual evidence from stops. PhD Thesis, MIT.","DOI":"10.21236\/ADA206826"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB20","doi-asserted-by":"crossref","unstructured":"Lamel, L., Gauvain, J.L., 1993. High performance speaker-independent phone recognition using CDHMM. In: Proc. Eurospeech, Vol. 1, pp. 121\u2013124.","DOI":"10.21437\/Eurospeech.1993-49"},{"issue":"11","key":"10.1016\/S0167-6393(97)00064-2_BIB21","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.1109\/29.46546","article-title":"Speaker-independent phone recognition using hidden markov models","volume":"37","author":"Lee","year":"1989","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(97)00064-2_BIB22","unstructured":"Leung, H.C., 1989. The use of artificial neural networks for phonetic recognition. PhD Thesis, MIT Department of Electrical Engineering and Computer Science."},{"key":"10.1016\/S0167-6393(97)00064-2_BIB23","doi-asserted-by":"crossref","unstructured":"Leung, H.C., Glass, J.R., Phillips, M.S., Zue, V.W., 1990. Detection and classification of phonemes using context-independent error back-propagation. In: Proc. ICSLP, Vol. 2, pp. 1061\u20131064.","DOI":"10.21437\/ICSLP.1990-278"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB24","doi-asserted-by":"crossref","unstructured":"Leung, H.C., Hetherington, I.L., Zue, V.W., 1991. Speech recognition using stochastic explicit-segment modeling. In: Proc. Eurospeech, Vol. 2, pp. 931\u2013934.","DOI":"10.21437\/Eurospeech.1991-223"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB25","doi-asserted-by":"crossref","unstructured":"Leung, H.C., Hetherington, I.L., Zue, V.W., 1992. Speech recognition using stochastic segment neural networks. In: Proc. Internat. Conf. Acoust. Speech Signal Process., Vol. 1, pp. 613\u2013616.","DOI":"10.1109\/ICASSP.1992.225834"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB26","doi-asserted-by":"crossref","unstructured":"Mari, J.F., Fohr, D., Junqua, J.C., 1996. A second-order HMM for high performance word and phoneme-based continuous speech recognition. In: Proc. Internat. Conf. Acoust. Speech Signal Process., Vol. 1, pp. 435\u2013438.","DOI":"10.1109\/ICASSP.1996.541126"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB27","unstructured":"Martens, J.-P., 1994. A connectionist approach to continuous speech recognition. In: Proc. FORWISS\/CRIM ESPRIT Workshop, pp. 26\u201333."},{"key":"10.1016\/S0167-6393(97)00064-2_BIB28","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/0167-6393(91)90029-S","article-title":"Broad phonetic classification and segmentation of continuous speech by means of neural network and dynamic programming","volume":"10","author":"Martens","year":"1991","journal-title":"Speech Communication"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB29","doi-asserted-by":"crossref","unstructured":"Martens, J.-P., Van Immerseel, L., 1990. An auditory model based on the analysis of envelope patterns. In: Proc. Internat. Conf. Acoust. Speech Signal Process., pp. 401\u2013404.","DOI":"10.1109\/ICASSP.1990.115713"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB30","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."},{"issue":"5","key":"10.1016\/S0167-6393(97)00064-2_BIB31","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."},{"issue":"3","key":"10.1016\/S0167-6393(97)00064-2_BIB32","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1002\/j.1538-7305.1986.tb00368.x","article-title":"A segmental k-means training procedure for connected word recognition","volume":"65","author":"Rabiner","year":"1986","journal-title":"AT&T Tech. J."},{"key":"10.1016\/S0167-6393(97)00064-2_BIB33","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1162\/neco.1991.3.4.461","article-title":"Neural network classifiers estimate Bayesian a posteriori probabilities","volume":"3","author":"Richard","year":"1991","journal-title":"Neural Computation"},{"issue":"2","key":"10.1016\/S0167-6393(97)00064-2_BIB34","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1109\/72.279192","article-title":"An application of recurrent nets to phone probability estimation","volume":"5","author":"Robinson","year":"1994","journal-title":"IEEE Trans. Neural Networks"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB35","doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J., 1986. Learning internal representations by error propagation. In: Rumelhart, D.E., McClelland, J.L. (Eds.), Parallel Distributed Processing: Exploration of the Microstructure of Cognition, Vol. 1: Foundations. MIT Press, Cambridge, MA.","DOI":"10.7551\/mitpress\/5236.001.0001"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB36","doi-asserted-by":"crossref","unstructured":"Siohan, O., Gong, Y., 1996. A semi-continuous stochastic trajectory model for phoneme-based continuous speech recognition. In: Proc. Internat. Conf. Acoust. Speech Signal Process., Vol. 1, pp. 471\u2013474.","DOI":"10.1109\/ICASSP.1996.541135"},{"issue":"6","key":"10.1016\/S0167-6393(97)00064-2_BIB37","doi-asserted-by":"crossref","first-page":"3511","DOI":"10.1121\/1.402840","article-title":"Pitch and voiced\/unvoiced determination with an auditory model","volume":"91","author":"Van Immerseel","year":"1992","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(97)00064-2_BIB38","doi-asserted-by":"crossref","unstructured":"Vereecken, H., Martens, J.-P., 1996. Noise suppression and loudness normalization in an auditory model-based acoustic front-end. In: Proc. ICSLP, Vol. 1, pp. 566\u2013569.","DOI":"10.1109\/ICSLP.1996.607180"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB39","unstructured":"Verhasselt, J., Martens, J.-P., Baeyens, B., 1996. Speech recognition using a discriminative context-independent, segment-based speech recognizer. In: Proc. IEEE ProRISC, pp. 367\u2013372."},{"key":"10.1016\/S0167-6393(97)00064-2_BIB40","doi-asserted-by":"crossref","unstructured":"Verhasselt, J., Illina, I., Martens, J.-P., Gong, Y., Haton, J.-P., 1997. The importance of segmentation probability in segment based speech recognizers. In: Proc. Internat. Conf. Acoust. Speech Signal Process., Vol. 2, pp. 1407\u20131410.","DOI":"10.1109\/ICASSP.1997.596211"},{"key":"10.1016\/S0167-6393(97)00064-2_BIB41","unstructured":"Werbos, P.J., 1974. Beyond regression: New tools for prediction and analysis in the behavioral sciences. PhD Thesis, Harvard University, Cambridge, MA."},{"issue":"3","key":"10.1016\/S0167-6393(97)00064-2_BIB42","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1109\/21.155943","article-title":"Methods of combining multiple classifiers and their applications to handwriting recognition","volume":"22","author":"Xu","year":"1992","journal-title":"IEEE Trans. Syst. Man Cybernet."},{"key":"10.1016\/S0167-6393(97)00064-2_BIB43","doi-asserted-by":"crossref","unstructured":"Zue, V., Glass, J., Phillips, M., Seneff, S., 1989. Acoustic segmentation and phonetic classification in the SUMMIT system. In: Proc. Internat. Conf. Acoust. Speech Signal Process., Vol. 1, pp. 389\u2013392.","DOI":"10.1109\/ICASSP.1989.266447"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639397000642?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639397000642?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2023,4,15]],"date-time":"2023-04-15T22:01:50Z","timestamp":1681596110000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639397000642"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1998,4]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[1998,4]]}},"alternative-id":["S0167639397000642"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6393(97)00064-2","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[1998,4]]}}}