{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T17:35:07Z","timestamp":1743010507345,"version":"3.30.1"},"reference-count":52,"publisher":"Elsevier BV","issue":"1","license":[{"start":{"date-parts":[[1999,2,1]],"date-time":"1999-02-01T00:00:00Z","timestamp":917827200000},"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":[[1999,2]]},"DOI":"10.1016\/s0167-6393(98)00067-3","type":"journal-article","created":{"date-parts":[[2003,4,5]],"date-time":"2003-04-05T03:57:58Z","timestamp":1049515078000},"page":"19-42","source":"Crossref","is-referenced-by-count":26,"title":["Parametric subspace modeling of speech transitions"],"prefix":"10.1016","volume":"27","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(98)00067-3_BIB1","doi-asserted-by":"crossref","unstructured":"Afify, M., Gong, Y., Haton, J.-P., 1994. Non-linear time alignment in stochastic trajectory models for speech recognition. In: Internat. Conf. in Spoken Language Processing, Vol. 1, pp. 291\u2013293","DOI":"10.21437\/ICSLP.1994-76"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB2","doi-asserted-by":"crossref","unstructured":"Afify, M., Gong, Y., Haton, J.-P., 1995. Stochastic trajectory models for speech recognition: An extension to modelling time correlation. In: European Conference on Speech Communication and Technology (Eurospeech), pp. 515\u2013518","DOI":"10.21437\/Eurospeech.1995-137"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB3","doi-asserted-by":"crossref","unstructured":"Ahlbom, G., Bimbot, F., Chollet, G., 1987. Modeling spectral speech transitions using temporal decomposition techniques. In: Internat. Conf. in Acoustics, Speech and Signal Processing, Vol. 1, pp. 13\u201316","DOI":"10.1109\/ICASSP.1987.1169742"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB4","doi-asserted-by":"crossref","unstructured":"Atal, B., 1983. Efficient coding of LPC parameters by temporal decomposition. In: Internat. Conf. in Acoustics, Speech and Signal Processing, Vol. 1, pp. 81\u201384","DOI":"10.1109\/ICASSP.1983.1172248"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB5","doi-asserted-by":"crossref","unstructured":"Bishop, C., 1995. Neural Networks for Pattern Recognition. Oxford University Press, Oxford","DOI":"10.1201\/9781420050646.ptb6"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB6","unstructured":"Bishop, C., Svensen, M., Williams, C., 1996. GTM: The Generative Topographic Mapping. NCRG\/96\/015, Neural Computing Research Group, Aston University, Birmingham"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB7","doi-asserted-by":"crossref","unstructured":"Bishop, C., Hinton, G., Strachan, I., 1997a. GTM through time. In: IEE International Conference on Artificial Neural Networks, pp. 111\u2013116","DOI":"10.1049\/cp:19970711"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB8","unstructured":"Bishop, C., Svensen M., Williams, C., 1997b. GTM: A principled alternative to the self-organizing map, Advances in Neural Information Processing Systems 9, 354\u2013360"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB9","doi-asserted-by":"crossref","unstructured":"Bourlard, H., Morgan, N., 1994. Connectionist Speech Recognition: A Hibrid Approach, Kluwer Academic Publishers, Dordrecht","DOI":"10.1007\/978-1-4615-3210-1"},{"issue":"368","key":"10.1016\/S0167-6393(98)00067-3_BIB10","doi-asserted-by":"crossref","first-page":"829","DOI":"10.2307\/2286407","article-title":"Robust locally weighted regression and smoothing scatterplots","volume":"74","author":"Cleveland","year":"1979","journal-title":"Journal of the American Statistical Association"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB11","unstructured":"Cole, R., Muthusamy, Y., Fanty, M., 1994. The ISOLET spoken letter database, Technical Report CSE 90-004, Oregon Graduate Institute"},{"issue":"4","key":"10.1016\/S0167-6393(98)00067-3_BIB12","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 Transactions on Speech and Audio Processing"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB13","unstructured":"Digalakis, V., 1992. Segment-based stochastic models of spectral dynamics for continuous speech recognition. Ph.D. Thesis, Boston University"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB14","doi-asserted-by":"crossref","unstructured":"Digalakis, V., Rohlicek, R., Ostendorf, M., 1991. A dynamical system approach to continuous speech recognition. In: Internat. Conf. in Acoustics, Speech and Signal Processing, Vol. 1, pp. 289\u2013292","DOI":"10.1109\/ICASSP.1991.150334"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB15","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1109\/89.242489","article-title":"ML estimation of a stochastic linear system with EM algorithm and its application to speech recognition","volume":"1","author":"Digalakis","year":"1993","journal-title":"IEEE Transactions of Speech and Audio Processing"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB16","unstructured":"Duda, R., Hart, P., 1973. Pattern Classification and Scene Analysis. Wiley, New York"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB17","unstructured":"Fisher, W., Doddington, G., Goudie-Marshall, K., 1986. The DARPA speech recognition research database: Specification and status. In: Proceedings of the Speech Recognition Workshop"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB18","doi-asserted-by":"crossref","first-page":"249","DOI":"10.2307\/2289161","article-title":"Exploratory projection pursuit","volume":"82","author":"Friedman","year":"1987","journal-title":"Journal of the American Statistical Association"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB19","doi-asserted-by":"crossref","unstructured":"Fukada, T., Sagisaka, Y., Paliwal, K., 1997. Model parameter estimation for mixture density polynomial segment models. In: Internat. Conf. Acoustics, Speech and Signal Processing, Vol. 2, pp. 1403\u20131406","DOI":"10.1109\/ICASSP.1997.596210"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB20","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(98)00067-3_BIB21","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":"Computer Speech and Language"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB22","doi-asserted-by":"crossref","unstructured":"Gish, H., Ng, K., 1996. Parametric trajectory models for speech recognition. In: Internat. Conf. in Spoken Language Processing, Vol. 1, pp. 466\u2013469","DOI":"10.1109\/ICSLP.1996.607155"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB23","doi-asserted-by":"crossref","unstructured":"Goldenthal, W., 1994. Statistical trajectory models for phonetic recognition. Ph.D. Thesis, Department of Aeronautics and Astronautics, MIT Press, Cambridge, MA","DOI":"10.1121\/1.409413"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB24","unstructured":"Gong, Y., Haton, J.-P. 1994. Stochastic trajectory modeling for speech recognition. In: Internat. Conf. in Acoustics, Speech and Signal Processing, Vol. 1, pp. 57\u201360"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB25","doi-asserted-by":"crossref","unstructured":"Gong, Y., Illina, I., Haton, J.-P., 1996. Modeling long term variability information in mixture stochastic trajectory framework. In: Internat. Conf. in Spoken Language Processing, Vol. 1, pp. 334\u2013337","DOI":"10.21437\/ICSLP.1996-109"},{"issue":"406","key":"10.1016\/S0167-6393(98)00067-3_BIB26","doi-asserted-by":"crossref","first-page":"502","DOI":"10.2307\/2289936","article-title":"Principal curves","volume":"84","author":"Hastie","year":"1989","journal-title":"Journal of the American Statistical Association"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB27","doi-asserted-by":"crossref","unstructured":"Holmes, W., Russell, M., 1997. Linear dynamic segmental HMMs: Variability representation and training procedure. In: Internat. Conf. in Acoustics, Speech and Signal Processing, Vol. 2, pp. 1399\u20131402","DOI":"10.1109\/ICASSP.1997.596209"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB28","doi-asserted-by":"crossref","unstructured":"Hu, Z., Barnard, E., 1997. Smoothness analysis for trajectory features. In: Internat. Conf. in Acoustics, Speech and Signal Processing, Vol. 2, pp. 979\u2013982","DOI":"10.1109\/ICASSP.1997.596103"},{"issue":"2","key":"10.1016\/S0167-6393(98)00067-3_BIB29","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1214\/aos\/1176349519","article-title":"Projection pursuit","volume":"13","author":"Huber","year":"1985","journal-title":"The Annals of Statistics"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB30","doi-asserted-by":"crossref","unstructured":"Kannan, A., Ostendorf, M., 1997. Adaptation of polynomial trajectory segment models for large vocabulary speech recognition. In: Internat. Conf. in Acoustics, Speech and Signal Processing, Vol. 2, pp. 1411\u20131414","DOI":"10.1109\/ICASSP.1997.596212"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB31","unstructured":"Lancaster, P., Salkauskas, K., 1986. Curve and Surface Fitting: An Introduction. Academic Press, New York"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB32","unstructured":"Marcus, S., van Lieshout, R., 1984. Temporal decomposition of speech. Annual Progress Report, IPO, Eindhoven, pp. 25\u201331"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB33","doi-asserted-by":"crossref","unstructured":"Marteau, P., Bailly, G., Janot-Giorgetti, M., 1988. Stochastic model of diphone-like segments based on trajectory concepts. In: Internat. Conf. in Acoustics, Speech and Signal Processing, Vol. 1, pp. 615\u2013618","DOI":"10.1109\/ICASSP.1988.196660"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB34","doi-asserted-by":"crossref","unstructured":"Niranjan, M., Fallside, F., 1987. On modelling the dynamics of speech patterns. In: European Conference on Speech Communication and Technology (Eurospeech), Vol. 1. pp. 71\u201374","DOI":"10.21437\/ECST.1987-21"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB35","unstructured":"Oja, E., 1983. Subspace Methods of Pattern Recognition, Research Studies Press, Letchworth, UK"},{"issue":"5","key":"10.1016\/S0167-6393(98)00067-3_BIB36","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 Transaction on Speech and Audio Processing"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB37","doi-asserted-by":"crossref","unstructured":"Rayner, M., Carter, D., Digalakis, V., Price, P., 1994. Combining knowledge sources to reorder N-best speech hypothesis lists. In: Proceedings of the 1994 ARPA Workshop on Human Language Technology","DOI":"10.3115\/1075812.1075858"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB38","doi-asserted-by":"crossref","unstructured":"Reinhard, K., Niranjan, M., 1997. Non linear speech transition visualization. In: IEE International Conference in Artificial Neural Networks, pp.257\u2013261","DOI":"10.1049\/cp:19970736"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB39","unstructured":"Reinhard, K., Niranjan, M., 1998. Parametric subspace modeling of speech transitions. Technical Report CUED\/F-INFENG\/TR.308, Cambridge University Engineering Department"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB40","doi-asserted-by":"crossref","unstructured":"Robinson, A., Bourlard, H., Hochberg, M., Kershaw, D., Morgan, D., Renals, S., 1996. A neural network based speaker independent, large vocabulary, continuous speech recognition system: The WERNICKE project. In: European Conference on Speech Communication and Technology (Eurospeech), pp.1941\u20131944","DOI":"10.21437\/Eurospeech.1993-401"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB41","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/0885-2308(91)90010-N","article-title":"A recurrent error propagation network speech recognition system","volume":"5","author":"Robinson","year":"1991","journal-title":"Computer Speech and Language"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB42","first-page":"650","article-title":"MOS and pair comparison combined methods for quality evaluation of text-to-speech systems","volume":"82","author":"Salza","year":"1996","journal-title":"Acustica"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB43","unstructured":"Schmid, P., 1996. Explicit N-best formant features for segment based speech recognition. Ph.D. Thesis, Oregon Graduate Institute"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB44","doi-asserted-by":"crossref","unstructured":"Schmid, P., Barnard, E., 1997. Explicit N-best formant features for vowel classification. In: Internat. Conf. in Acoustics, Speech and Signal Processing, Vol. 2, pp. 991\u2013994","DOI":"10.1109\/ICASSP.1997.596106"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB45","doi-asserted-by":"crossref","unstructured":"Schwartz, R., Klovstad, J., Makhoul, J., Klatt, D., Zue, V., 1979. Diphone synthesis for phonetic vocoding. In: Internat. Conf. in Acoustics, Speech and Signal Processing, Vol. 1, pp. 891\u2013894","DOI":"10.1109\/ICASSP.1979.1170600"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB46","doi-asserted-by":"crossref","unstructured":"Sun, D., 1997. Statistical modeling of co-articulation in continuous speech based on data driven interpolation. In: Internat. Conf. in Acoustics, Speech and Signal Processing, Vol. 3, pp. 1751\u20131754","DOI":"10.1109\/ICASSP.1997.598863"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB47","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1007\/BF01889678","article-title":"Principal curves revisited","volume":"2","author":"Tibshirani","year":"1992","journal-title":"Statistics and Computing"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB48","unstructured":"Valtchev, V., 1995. Discriminative Methods in HMM-based speech recognition. Ph.D. Thesis, Cambridge University Engineering Department"},{"issue":"3","key":"10.1016\/S0167-6393(98)00067-3_BIB49","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1109\/29.21701","article-title":"Phoneme recognition using time-delay neural networks. IEEE Transactions on Acoustics","volume":"37","author":"Waibel","year":"1989","journal-title":"Speech and Signal Processing"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB50","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"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB51","unstructured":"Young, S., Jansen, J., Odell, J., Ollason, D., Woodland, P., 1995. The HTK Book, Version 2.0. Entropic Cambridge Research Laboratory and University of Cambridge"},{"key":"10.1016\/S0167-6393(98)00067-3_BIB52","unstructured":"Zue, V., 1991. Speech spectrogram reading: An acoustic study of the English language, Lecture Notes, MIT Press, Cambridge, MA"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639398000673?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639398000673?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T04:22:01Z","timestamp":1733458921000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639398000673"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1999,2]]},"references-count":52,"journal-issue":{"issue":"1","published-print":{"date-parts":[[1999,2]]}},"alternative-id":["S0167639398000673"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6393(98)00067-3","relation":{},"ISSN":["0167-6393"],"issn-type":[{"type":"print","value":"0167-6393"}],"subject":[],"published":{"date-parts":[[1999,2]]}}}