{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T05:39:43Z","timestamp":1775281183655,"version":"3.50.1"},"reference-count":70,"publisher":"Elsevier BV","issue":"4","license":[{"start":{"date-parts":[[1998,7,1]],"date-time":"1998-07-01T00:00:00Z","timestamp":899251200000},"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":[[1998,7]]},"DOI":"10.1016\/s0167-6393(98)00023-5","type":"journal-article","created":{"date-parts":[[2003,4,5]],"date-time":"2003-04-05T03:57:58Z","timestamp":1049515078000},"page":"299-323","source":"Crossref","is-referenced-by-count":52,"title":["A dynamic, feature-based approach to the interface between phonology and phonetics for speech modeling and recognition"],"prefix":"10.1016","volume":"24","author":[{"given":"Li","family":"Deng","sequence":"first","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/S0167-6393(98)00023-5_BIB1","unstructured":"R. Bakis Coarticulation modeling with continuous-state HMMs, (as described in Section 4.1) Proc. IEEE Workshop Automatic Speech Recognition, Arden House, NY, 1991, pp. 20\u201321"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB2","doi-asserted-by":"crossref","unstructured":"P. Beddor, T. Toon (Eds.), Linguistic Approaches to Phonetics (special issue), J. Phonetics 18 (1990)","DOI":"10.1016\/S0095-4470(19)30390-0"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB3","doi-asserted-by":"crossref","unstructured":"C.M. Bishop, Neural Networks for Pattern Recognition, Clarendon Press, Oxford, 1995","DOI":"10.1201\/9781420050646.ptb6"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB4","doi-asserted-by":"crossref","unstructured":"C. Blackburn, S. Young, Towards improved speech recognition using a speech production model, Proc. Euro-speech, vol. 2, 1995, pp. 1623\u20131626","DOI":"10.21437\/Eurospeech.1995-393"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB5","doi-asserted-by":"crossref","unstructured":"J. Blevins, The syllable in phonological theory, in: J. Goldsmith (Ed.), The Handbook of Phonological Theory, Blackwell Science, Cambridge, 1995, pp. 206\u2013244","DOI":"10.1111\/b.9780631201267.1996.00008.x"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB6","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1016\/0167-6393(96)00003-9","article-title":"Towards increasing speech recognition error rates","volume":"18","author":"Bourlard","year":"1996","journal-title":"Speech Commun."},{"key":"10.1016\/S0167-6393(98)00023-5_BIB7","doi-asserted-by":"crossref","unstructured":"C. Browman, L. Goldstein, Towards an articulatory phonology, Phonology Yearbook, vol. 3, 1986, pp. 219\u2013252","DOI":"10.1017\/S0952675700000658"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB8","first-page":"603","article-title":"Bayesian back-propagation","volume":"5","author":"Buntine","year":"1991","journal-title":"Complex Syst."},{"key":"10.1016\/S0167-6393(98)00023-5_BIB9","doi-asserted-by":"crossref","unstructured":"K. Church, Phonological Parsing in Speech Recognition, Kluwer Academic Publishers, Dordrect, 1987","DOI":"10.1007\/978-1-4613-2013-5"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB10","doi-asserted-by":"crossref","unstructured":"N. Clements, The geometry of phonological features, Phonology Yearbook, vol. 2, 1985, pp. 225\u2013252","DOI":"10.1017\/S0952675700000440"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB11","unstructured":"J. Cohen, The summers of our discontent, Proc. Addendum ICSLP, 1996, pp. S9\u201310"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB12","first-page":"1","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"B\u201339","author":"Dempster","year":"1977","journal-title":"J. Royal Statist. Soc."},{"key":"10.1016\/S0167-6393(98)00023-5_BIB13","unstructured":"P. Denes, E. Pinson, The Speech Chain \u2013 The Physics and Biology of Spoken Language, Doubleday, New York, 1973"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB14","unstructured":"L. Deng, Speech modeling and recognition using a time series model containing trend functions with Markov modulated parameters, Proc. IEEE Workshop Automatic Speech Recognition, Arden House, NY, 1991, pp. 24\u201326"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB15","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/0165-1684(92)90112-A","article-title":"A generalized hidden Markov model with state-conditioned trend functions of time for the speech signal","volume":"27","author":"Deng","year":"1992","journal-title":"Signal Processing"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB16","unstructured":"L. Deng, A computational model of the phonology-phonetics interface for automatic speech recognition, Summary Report, SLS-LCS, Massachusetts Institute of Technology, 1992\u20131993"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB17","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1109\/89.242494","article-title":"A stochastic model of speech incorporating hierarchical nonstationarity","volume":"1","author":"Deng","year":"1993","journal-title":"IEEE Trans. Speech and Audio Processing"},{"issue":"4","key":"10.1016\/S0167-6393(98)00023-5_BIB18","doi-asserted-by":"crossref","first-page":"2318","DOI":"10.1121\/1.406375","article-title":"Design of a feature-based speech recognizer aiming at integration of auditory processing, signal modeling, and phonological structure of speech","volume":"93","author":"Deng","year":"1993","journal-title":"J. Acoust. Soc. Am., part 2"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB19","unstructured":"L. Deng, A computational model of the phonology-phonetics integration for automatic speech recognition, Proc. IEEE Workshop Automatic Speech Recognition, Snowbird, Utah, 1993, pp. 83\u201384"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB20","doi-asserted-by":"crossref","unstructured":"L. Deng, Integrated-multilingual speech recognition using universal phonological features in a functional speech production model. Proc. ICASSP, Munich, vol. 2, 1997, pp. 1007\u20131010","DOI":"10.1109\/ICASSP.1997.596110"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB21","doi-asserted-by":"crossref","unstructured":"L. Deng, Computational models for speech production, in: Computational Models of Speech Pattern Processing (NATO ASI) (in press)","DOI":"10.1007\/978-3-642-60087-6_20"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB22","unstructured":"L. Deng, Computational models for auditory speech processing, in Computational Models of Speech Pattern Processing (NATO ASI) (in press)"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB23","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 Proc."},{"key":"10.1016\/S0167-6393(98)00023-5_BIB24","doi-asserted-by":"crossref","first-page":"2008","DOI":"10.1121\/1.410144","article-title":"Context-dependent Markov model structured by locus equations: Applications to phonetic classification","volume":"96","author":"Deng","year":"1994","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/S0167-6393(98)00023-5_BIB25","unstructured":"L. Deng, G. Ramsay, H. Sameti, From modeling surface phenomena to modeling mechanisms: Towards a faithful model of the speech process aiming at speech recognition, Proc. IEEE Workshop Automatic Speech Recognition, Snowbird, 1995, pp. 183\u2013184"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB26","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/S0167-6393(97)00018-6","article-title":"Production models as a structural basis for automatic speech recognition","volume":"22","author":"Deng","year":"1997","journal-title":"Speech Commun."},{"key":"10.1016\/S0167-6393(98)00023-5_BIB27","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1109\/89.506934","article-title":"Transitional speech units and their representation by the regressive Markov states","volume":"4","author":"Deng","year":"1996","journal-title":"IEEE Trans. Speech Audio Proc."},{"key":"10.1016\/S0167-6393(98)00023-5_BIB28","doi-asserted-by":"crossref","first-page":"2702","DOI":"10.1121\/1.409839","article-title":"A statistical approach to automatic speech recognition using the atomic speech units constructed from overlapping articulatory features","volume":"95","author":"Deng","year":"1994","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/S0167-6393(98)00023-5_BIB29","doi-asserted-by":"crossref","unstructured":"L. Deng, J. Wu, Hierarchical partitioning of articulatory state space for articulatory-feature based speech recognition, Proc. ICSLP, Philadelphia, 1996, pp. 2266\u20132269","DOI":"10.21437\/ICSLP.1996-295"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB30","doi-asserted-by":"crossref","unstructured":"L. Deng, J. Wu, H. Sameti, Improved speech modeling and recognition using multi-dimensional articulatory states as primitive speech units, Proc. ICASSP, Detroit, 1995, pp. 385\u2013388","DOI":"10.1109\/ICASSP.1995.479602"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB31","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1109\/89.242489","article-title":"ML estimation of a stochastic linear system with the EM algorithm and its application to speech recognition","volume":"1","author":"Digalakis","year":"1993","journal-title":"IEEE Trans. Speech and Audio Proc."},{"issue":"4","key":"10.1016\/S0167-6393(98)00023-5_BIB32","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1250\/ast.5.233","article-title":"Analysis of voice fundamental frequency contours for declarative sentences of Japanese","volume":"5","author":"Fujisaki","year":"1984","journal-title":"J. Acoust. Soc. Japan"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB33","doi-asserted-by":"crossref","unstructured":"S. Furui, Flexible speech recognition, Proc. Eurospeech, vol. 3, 1995, pp. 1595\u20131603","DOI":"10.21437\/Eurospeech.1995-4"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB34","unstructured":"J. Goldsmith (Ed.), The Handbook of Phonological Theory, Blackwell Science, Cambridge, 1995"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB35","unstructured":"S. Greenberg, Understanding speech understanding: Towards a unified theory of speech perception, Proc. ESCA Tutorial and Research Workshop on the Auditory Basis of Speech Perception, Keele University, UK, 1996, pp. 1\u20138"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB36","unstructured":"S. Greenberg, On the origins of speech intelligibility in the real world, Proc. ESCA Workshop on Robust Speech Recognition for Unknown Communication Channels, Pont-a-Mousson, France, 1997, pp. 23\u201332"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB37","unstructured":"W. Hardcastle, J. Laver (Eds.), The Handbook of Phonetic Sciences, Blackwell Science, Cambridge, 1997"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB38","doi-asserted-by":"crossref","unstructured":"J. Holmes, W. Holmes, P. Garner, Using formant frequencies in speech recognition, Proc. Eurospeech, Rhodes, Greece, vol. 4, 1997, pp. 2083\u20132086","DOI":"10.21437\/Eurospeech.1997-551"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB39","unstructured":"Q. Huo, C.-H. Lee, A Bayesian predictive classification approach to robust speech recognition, IEEE Trans. Speech Audio Proc. (in press)"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB40","doi-asserted-by":"crossref","unstructured":"F. Jelinek, Continuous speech recognition by statistical methods, Proc. of the IEEE, vol. 64, 1976, pp. 532\u2013556","DOI":"10.1109\/PROC.1976.10159"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB41","unstructured":"P. Keating, The phonology\u2013phonetics interface, In: F. Newmeyer (Ed.), Linguistics: The Cambridge Survey. I. Linguistics Theory, Cambridge University Press, Cambridge, 1988, pp. 281\u2013302"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB42","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1017\/S0952675700001950","article-title":"Feature geometry and the vocal tract","volume":"11","author":"Keyser","year":"1994","journal-title":"Phonology"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB43","doi-asserted-by":"crossref","first-page":"1032","DOI":"10.2307\/2289375","article-title":"Non-Gaussian state-space modeling of nonstationary time series (with discussions)","volume":"82","author":"Kitagawa","year":"1987","journal-title":"J. Am. Stat. Assoc."},{"key":"10.1016\/S0167-6393(98)00023-5_BIB44","doi-asserted-by":"crossref","unstructured":"G. Kitagawa, W. Gersch, Smoothness Priors Analysis of Time Series, Springer, New York, 1996","DOI":"10.1007\/978-1-4612-0761-0"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB45","unstructured":"P. Ladefoged, I. Maddieson, The Sounds of the World's Languages, Blackwell Science, Oxford, 1996"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB46","unstructured":"N. Lass (Ed.), Principles of Experimental Phonetics, Mosby, London, 1995"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB47","doi-asserted-by":"crossref","unstructured":"C.-H. Lee, F. Soong, K. Paliwal (Eds.), Automatic Speech and Speaker Recognition \u2013 Advanced Topics, Kluwer Academic Publishers, Dordrecht, 1996","DOI":"10.1007\/978-1-4613-1367-0"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB48","doi-asserted-by":"crossref","unstructured":"W. Levelt, Speaking \u2013 From Intention to Articulation, MIT Press, Cambridge, MA, 1989","DOI":"10.7551\/mitpress\/6393.001.0001"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB49","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1162\/neco.1992.4.3.415","article-title":"Bayesian interpolation","volume":"4","author":"MacKay","year":"1992","journal-title":"Neural Comput."},{"key":"10.1016\/S0167-6393(98)00023-5_BIB50","doi-asserted-by":"crossref","unstructured":"I. Maddieson, Patterns of Sounds, Cambridge University Press, Cambridge, 1984","DOI":"10.1017\/CBO9780511753459"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB51","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1016\/S0095-4470(19)30348-1","article-title":"On articulatory and acoustic variabilities","volume":"19","author":"Maeda","year":"1991","journal-title":"J. Phonetics"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB52","unstructured":"J. Mendel, Lessons in Estimation Theory for Signal Processing, Communications, and Control, Prentice-Hall, Englewood Cliffs, NJ 1995"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB53","doi-asserted-by":"crossref","unstructured":"H. Meng, Phonological Parsing for Bi-Directional Letter-to-Sound\/Sound-to-Letter Generation, Ph.D. dissertation, MIT, 1995","DOI":"10.21236\/ADA458591"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB54","unstructured":"R. Moore, What is speech pattern processing and where do we go from here?, in: Computational Models of Speech Pattern Processing (NATO ASI) (in press)"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB55","doi-asserted-by":"crossref","unstructured":"N. Morgan, H. Bourlard, Connectionist Speech Recognition \u2013 A Hybrid Approach, Kluwer Academic Publishers, Dordrecht, 1994","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB56","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1109\/89.536930","article-title":"From HMMs to segment models: A unified view of stochastic modeling for speech recognition","volume":"4","author":"Ostendorf","year":"1996","journal-title":"IEEE Trans. Speech Audio Proc."},{"key":"10.1016\/S0167-6393(98)00023-5_BIB57","unstructured":"M. Ostendorf, From HMMs to segment models: A unified view, in Computational Models of Speech Pattern Processing (NATO ASI) (in press)"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB58","unstructured":"J. Perkell, Phonetic features and the physiology of speech production, in: B. Butterworth (Ed.), Language Production, Academic Press, London, 1980"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB59","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/S0095-4470(95)80030-1","article-title":"Goal-based speech motor control: A theoretical framework and some preliminary data","volume":"23","author":"Perkell","year":"1995","journal-title":"J. Phonetics"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB60","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1109\/72.279191","article-title":"Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks","volume":"5","author":"Puskorius","year":"1994","journal-title":"IEEE Trans. Neural Networks"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB61","doi-asserted-by":"crossref","unstructured":"L. Rabiner, B.-H. Juang, C.-H. Lee, An overview of automatic speech recognition, in: Automatic Speech and Speaker Recognition \u2013 Advanced Topics, Kluwer Academic Publishers, Dordrecht, 1996, pp. 1\u201330","DOI":"10.1007\/978-1-4613-1367-0_1"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB62","doi-asserted-by":"crossref","unstructured":"G. Ramsay, L. Deng, Optimal filtering and smoothing for articulatory speech recognition using a stochastic target model, Proc. ICSLP, vol. 2, 1996, pp. 1113\u20131116","DOI":"10.21437\/ICSLP.1996-292"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB63","unstructured":"P. Rubin, E. Saltzman, L. Goldstein, R. McGowan, M. Tiede, C. Browman, CASY and extensions to the task-dynamic model, Proc. 4th European Speech Production Workshop, Autrans, France, 1996, pp. 125\u2013128"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB64","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1207\/s15326969eco0104_2","article-title":"A dynamical approach to gestural patterning in speech production","volume":"1","author":"Saltzman","year":"1989","journal-title":"Ecolog. Psychol."},{"key":"10.1016\/S0167-6393(98)00023-5_BIB65","unstructured":"E. Selkirk, The Syllable, in: H. Hulst, N. Smith (Eds.), The Structure of Phonological Representation, Foris Publications, 1982, pp. 337\u2013383"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB66","unstructured":"J. Spall (Ed.), Bayesian Analysis of Time Series and Dynamic Models, Marcel Dekker, New York, 1988"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB67","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/S0095-4470(19)31520-7","article-title":"On the quantal nature of speech","volume":"17","author":"Stevens","year":"1989","journal-title":"J. Phonetics"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB68","unstructured":"M. West, J. Harrison, Bayesian Forecasting and Dynamic Models, 2nd ed., Springer, New York, 1997"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB69","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1214\/aos\/1176346060","article-title":"On the convergence properties of the EM algorithm","volume":"11","author":"Wu","year":"1983","journal-title":"The Annals of Statistics"},{"key":"10.1016\/S0167-6393(98)00023-5_BIB70","unstructured":"V. Zue, Notes on speech spectrogram reading, Course Notes, MIT, Cambridge, MA , 1991"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639398000235?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639398000235?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T08:58:45Z","timestamp":1733302725000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639398000235"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1998,7]]},"references-count":70,"journal-issue":{"issue":"4","published-print":{"date-parts":[[1998,7]]}},"alternative-id":["S0167639398000235"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6393(98)00023-5","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[1998,7]]}}}