Automatyczne rozpoznawanie mowy bazujące na ukrytych modelach Markowa : problemy i metody

• Autorzy: Wiśniewski A. M.
• Języki publikacji: PL

Abstrakty

PL

Przedstawiono problemy i metody ich rozwiązania w procesie tworzenia systemu automatycznego rozpoznawania mowy bazującego na ukrytych modelach Markowa.

Słowa kluczowe

PL

model Markova; rozpoznawanie mowy automatyczne

• Wydawca: Instytut Teleinformatyki i Automatyki, Wydział Cybernetyki, Wojskowa Akademia Techniczna im. Jarosława Dąbrowskiego
• Czasopismo: Biuletyn Instytutu Automatyki i Robotyki
• Rocznik: 2000
• Tom: R. 6, nr 12
• Strony: 3--83
• Opis fizyczny: Bibliogr. 128 poz.

Twórcy

autor

Wiśniewski A. M.

• Zakład Automatyki, Instytut Automatyki i Robotyki WAT, ul. S. Kaliskiego 2, 00-908 Warszawa

Bibliografia

• [1] Adamczyk B., Adamczyk K., Trawiński K., Zasób mowy ROBOT. Biuletyn IAiR WAT, nr 12, 2000.
• [2] Aizerman M. A., Rozonoer E. M. B. L. I., Theoretical Foundations of the Potential Function Method in Pattern Recognition Learning and The Probability Problem of Pattern Recognition Learning and the Method of Potential Functions. In Automation and Remote Control vol. 25, pp. 821837/1175-1193, 1964.
• [3] Aust H., Oerder M., A Real Time Prototype of an Automatic Inquiry System. In 1994 Inter. Conf. on Spoken Language Processing, pp. 703-706, Yokohama, 1994.
• [4] Aust H., Oerder M., Seide F., and Steinbiss V., Experience with the Philips automatic train timetable information system. In Proceedings 2nd IEEE Workshop on Interactive Voice Technology for TLC Applications IVTTA 97, Yokohama, 1994.
• [5] Austin S., Schwartz R., Placeway P., The Forward-Backward Search I Algorithm. In Proceedings ICASSP 91, pp. 697-700, Toronto, 1991.
• [6] Baggia P., Gerbino E., Giachin E., Rullent C., Efficient representation of linguistic knowledge in continuous speech understanding. In Proceedings IJCAI 91, Sydney, 1991.
• [7] Bahl L. R., Brown P. F., de Souza P. V., Mercer R. L., A Tree Based Statistical Language Model for Natural Language Speech Recognition. In IEEE Trans. on Acoustics, Speech and Signal Processing, vol. 37, pp. 10011008, 1989.
• [8] Bahl L. R., de Souza P. V., Gopalkrishnan P. S., Nahamoo D., Picheny M. A., Context Dependent Modelling of Phones in Continuous Speech using Decision Trees. In Proceedings DARPA Speech and Natural Language Processing Workshop, pp. 264-27 D, 1991.
• [9] Bahl L. R., Jelinek F., Mercer R. L., A Maximum Likelihood Approach to Continuous Speech Recognition. In IEEE Trans, on Pattern Analysis and Machine Intelligence, vol. 5, pp. 179-190, (1983).
• [10] Bahl L. R., Jelinek F., Mercer R. L., Nadas A., Next Word Statistical Predictor. IBM Tech. Disclosure Bulletin, 27 (7A): 3941-42, 1984.
• [11] Bahl L. R., Mercer R., Part-of Speech Assignment by a Statistical Decision Algorithm. In International Symposium on Information Theory, Ronneby, Sweden, 1976.
• [12] Baker J. K., The Dragon System - an Overview. IEEE Trans ASSP, 23(1): 24-29, 1975.
• [13] Baldi P., Chauvin Y., Hunkapiller T., McClure M. A., Hidden Markov-Models of Biological Primary Sequence Information. Proceedings of the National Academy of Sciences of the United States, 91 (3): 1059-1063, 1994.
• [14] Basztura Cz. i inni, Statystyczny opis cech mierzalnych mowy polskiej. Prace naukowe ITiA Politechniki Wrocławskiej, nr 29, 1989.
• [15] Basztura Cz. i inni, Metody parametryzacji sygnału mowy do automatycznego rozpoznawania głosów. Prace Naukowe ITiA Politechniki Wrocławskiej, nr 31, 1990.
• [16] Basztura Cz. i inni, Modele analizy i procedury w komputerowym rozpoznawaniu głosów. Prace Naukowe ITiA Politechniki Wrocławskiej, nr 30, 1989.
• [17] Basztura Cz., Rozmawiać z komputerem. Wydawnictwo FORMAT, Wrocław, 1992.
• [18] Baum L. E., An inequality and associated maximization technique in statistical estimation for probabilistic functions of a Markov process. Inequalities, 3: p. 1-8, 1972.
• [19] Baum L. E., Petrie T., Soules G., Weiss N., A maximisation technique occurring in the statistical analysis of probabilistic functions of Markov chains. Annals of Mathematical Statistics, 41: 164-171, 1970.
• [20] Beauchamp K.G., Przetwarzanie sygnałów metodami analogowymi i cyfrowymi. WNT, Warszawa, 1978.
• [21] Bell T. C., Cleary J. G., Witten I. A., Text Compression. Prentice Hall, Englewood Cliffs, NJ, 1990.
• [22] Bourlard H. Morgan N., Continuous Speech Recognition by Connectionist Statistical Methods. In IEEE Trans. on Neural Networks, number 6 in 4, pp. 893-909, 1994.
• [23] Breiman L., Friedman J. H., Olshen R. A., Stone C. J., Classification and Regression Trees. Wadsworth, Monterey, CA, 1984.
• [24] Brown P., Pietra V. D., de Souza P., Lai J., Mercer, R., Class-Based n-gram Models of Natural Language. Computational Linguistics, 18(4): 467-479, 1992.
• [25] Calder J., Klein E., Zeevat H., Unification categorial grammar: a concise extendable grammar for natural language processing. In Proceedings Coling-88, pp. 83-86, Budapest, 1988.
• [26] Charniak E., Tree-bank grammars. In Proceedings AAAI-96, Portland, OR, 1996.
• [27] Church K., Gale W. A. A Comparison of the Enhanced Good-Turing and Deleted Estimation Methods for Estimating Probabilities of English Bigrams. Computer, Speech and Language, 5: 19-54, 1991.
• [28] Church K., Mercer R. Introduction to the Special Issue on Computational Linguistics Using Large Corpora. Computational Linguistics, 19(1): 1-24, 1993.
• [29] Cole R.A., Mariani J., Uszkoreit J., Zaenen A., Zue Victor Survey of the State of the Art. in Human Language Technology. Center for Spoken Language Understanding, Oregon Graduate Institut, University of Pisa, Italy.
• [30] Corazza A., de Mori R., Gretter R., Satta G., Recent results on stochastic language modeling. Technical report, CRIM/FORWISS Workshop, Manchen, 1994.
• [31] Deller J. R., Proakis J. G., Hansen J. H., Discrete-Time Processing of Speech Signals. Macmillan Publishing co., New York, 1993.
• [32] Deming W., Some Theory of Sampling. Dover Publications, New York, 1966.
• [33] Derouault A. M., Merialdo B., Natural Language Modeling for Phoneme-to-Text Transcription. In IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 8, pp. 742-749, 1986.
• [34] Donovan R. E., Woodland P. C., Automatic Speech Synthesiser Parameter Estimation using HMMs. In Proceedings ICASSP 95, vol. 1, pp. 640-643, Detroit, M, 1995.
• [35] Duda R. O., Hart P. E., Pattern Classification and Scene Analysis. J. Wiley & Sons, New York, 1973.
• [36] Dugad R., Desai U.B., A tutorial on hidden Markov models. http://www.ee.iitb.ernet.in:80/spann/thesis/Tech_Reports/HMM_TUT/hmm_tut.html
• [37] Feldweg H„ Implementation and evaluation of a German HMM for POS disambiguation. In SIGDAT- 95 (EACL-93 Workshop), Dublin, 1995.
• [38] Fenk-Oczlon G., Word frequency and word order in freezes. In Linguistics, vol. 27, pp. 517-556, 1989.
• [39] Fissore F., Giachin E., Laface P., Massafra P., Using grammars in forward and backward search. In Proceedings Eurospeech 93, Berlin, 1993.
• [40] Fissore L„ Laface P., Micca G., Comparison of discrete and continuous HMMs in a CSR task over the telephone. In Proceedings ICASSP 91, Toronto, 1991.
• [41] Fissore L., Laface P., Micca G., Pieraccini R., Lexical access to very large vocabularies. In IEEE Trans. on ASSP, vol. 37(8), 1989.
• [42] Forney G.D., The Viterbi algorithm. Proc. IEEE, vol. 61, p. 268-278, March 1973.
• [43] Fu K. S., Syntactic Methods in Pattern Recognition. .Academic Press, London/New York, 1974.
• [44] Fu, K. S., Booth T. L., Grammatical Inference: Introduction and Survey. IEEE Trans. on System, Man and Cybernetics, 5. In two parts, 1975.
• [45] Generet N., Ney H., Wessel F., Extensions of Absolute Discounting for Language Modelling. In Fourth European Conference on Speech Communication and Technology, pp. 1245-1248, Madrid, 1995.
• [46] Giachin E., Automatic training of stochastic finite-state language models for speech understanding. In Proceedings ICASSP 92, San Francisco, 1992.
• [47] Giachin E., Phrase bigrams for continuous speech recognition. In Proceedings ICASSP 95, Detroit, MI, 1995.
• [48] Giachin E., Baggia P., Micca G., Language models for spontaneous speech recognition: a bootstrap method for learning phrase bigrams. In Proceedings ICSLP 94, Yokohama, 1994.
• [49] Giachin E., Rullent C., Linguistic processing in a speech understanding system. In Laface P., de Mori R., (eds.), NATO Workshop on Speech Recognition and Understanding 1990, Cetraro. Springer-Verlag, Berlin, 1992.
• [50] Gibbon D., Moore R., and Winski R., Handbook of Standards and Resources for Spoken Language Systems. Walter de Gruyter Publishers, Berlin & New York, 1997.
• [51] Gilloux M., Leroux M., Bertille J. M., Strategies for Cursive Script Recognition Using Hidden Markov Models. Machine Vision and Applications, 8(4): 197-205, 1995.
• [52] Harris Z., From morpheme to utterance. Language, 22, 1946.
• [53] Jelinek F., Continuous Speech Recognition by Statistical Methods. IEEE, 64(4): 532-556, 1976.
• [54] Jelinek F., The Development of an Experimental Discrete Dictation Recognizer. In IEEE 85, 1985.
• [55] Jelinek F., Self-Organized Language Modeling for Speech Recognition. In Waibel A., Lee K. F., (eds.), Readings in Speech Recognition, pp. 450-506. Morgan-Kaufmann Publishers Inc., San Mateo, CA, 1991.
• [56] Jelinek F., Bahl L. R., Mercer R. L., Design of a Linguistic Statictical Decoder for the Recognition of Continuous Speech. IEEE Transactions on Information Theory, 21(3): 250-256, 1975.
• [57] Jelinek F., Lafferty J., Mercer R. L., Basic Methods of Probabilistic Context Free Grammars. In Laface P., de Mori R., (eds.), Speech Recognition and Understanding, pp. 347-360. Springer-Verlag, Berlin, 1992.
• [58] Jelinek F., Mercer R., Probability Distribution Estimation from Sparse Data. In IBM Technical Disclosure Bulletin, vol. 28, pp. 2591-2594, 1985.
• [59] Jelinek F., Mercer R. L., Interpolated estimation of Markov source parameters from sparse data. In Gelsema, E. S. and Kanal, L. N., (eds.), Pattern Recognition in Practice, pp. 381-397. North Holland Publishing Company, Amsterdam, 1980.
• [60] Jelinek F., Mercer R. L., Roukos S., Classifying Words for Improved Statistical Language Models. In IEEE Inter. Conf. on Acoustics, Speech and Signat Processing, pp. 621-624, Albuquerque, NM, 1990.
• [61] Jelinek F., Mercer R. L., Roukos S., Principles of Lexical Language Modeling for Speech Recognition. In Furui S., Sondhi M. M., (eds.), Advances ire Speech Signal Processing, pp. 651-699. Marcel Dekker, New York, 1991 a.
• [62] Jelinek F., Merialdo B., Roukos S., Strauss M., A Dynamic Language Model for Speech Recognition. In Proceedings of the DARPA Workshop Speech and Natural Language Workshop, pp. 293-295, Pacific Grove, CA, 1991 b.
• [63] Juang В. H., Maximum likelihood estimation for mixture multivariate stochastic observations of Markov chains. AT&T Technical Journal, 64: 1235-1249, 1985.
• [64] Juang B.H., Rabiner L.R., The segmental к-means algorithm for estimating parameters of hidden Markov models. IEEE Trans. Acoust. Speech Signal Processing, vol. 38, no. 9, p. 1639-1641, September 1990.
• [65] Katz S. M., Estimation of Probabilities from Sparse Data for the Language Model Component of a Speech Recogniser. IEEE Trans. ASSP, 35(3): 400-401, 1987.
• [66] Keller E., Fundamentals of Speech Synthesis and Speech Recognition. Basic Concepts, State of the Art. and Future Challenges. John Wiley & Sons, 1995.
• [67] Kuhn R., de Mori R., A Cache-Based Natural Language Model for Speech Recognition. In IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 12, pp. 570-583, 1990.
• [68] Laface P., de Mori R., Speech Recognition and Understanding. Recent Advances, Trends and Applications. Springer-Verlag, 1990.
• [69] Lafferty J., Sleator D., Temperley D., Grammatical Trigrams: A Probabilistic Model of Link Grammars. In Proceedings AAA1 Fall Symposium on Probabilistic Approaches to Natural Language, Cambridge, MA. (Also) Technical Report CMU-CS-92-181, Carnegie Mellon University, Pittsburgh, CA, 10 pages, 1992.
• [70] Lau R., Rosenfeld R., Roukos S., Trigger-Based Language Models: A Maximum Entropy Approach. In Proceedings IEEE Inter. Conf. on Acoustics, Speech and Signal Processing, vol. II, pp. 45-48, Minneapolis, MN, 1993.
• [71] Lee С. H., Rabiner L. R., Pieraccini R., Wilpon J. G., Acoustic modeling for large vocabulary speech recognition. Computer Speech and Language, 4, 1990.
• [72] Lee K. F., Automatic speech recognition: the development of the SPHINX system. Kluwer Academic Publishers, Dordrecht, 1989.
• [73] Lee K. F., Context-Dependent Phonetic Hidden Markov Models for Speaker-Indepent Continuous Speech Recognition. IEEE Trans. ASSP, 38(4): 599-609, 1990.
• [74] Levinson S. E., Continuously Variable Duration Hidden Markov Models for Automatic Speech Recognition. Computer Speech and Language, 1(1): 29-45, 1986.
• [75] Marcus M., A Theory of Syntactic Recognition for Natural Language. MIT Press, Cambridge, MA, 1980.
• [76] Marcus M., Santorini B., Marcinkiewicz M., Building a Large Annotated Corpus of English: the Penn Treebank. In Computational Linguistics, vol. 19(2), 1993.
• [77] Nadas A., Optimal Solution of a Training Problem in Speech Recognition. In IEEE Trans. on Acoustics, Speech and Signal Processing, vol. ASSP-33, pp. 326-329, 1983.
• [78] Nadas A., Estimation of Probabilities in the Language Model of the IBM Speech Recognition System. In IEEE Trans. on Acoustics, Speech and Signal Processing, vol. 32, pp. 859-861, 1984.
• [79] Ney H., The use of a one-stage dynamic programming algorithm for connected word recognition. In IEEE Transactions on ASSP, vol. 32, 1984.
• [80] Ney H., Aubert X., A word graph algorithm for large vocabulary, continuous speech recognition. In 1994 ICSLP, pp. 1355-1358. Yokohama, Japan, 1994.
• [81] Ney H., Essen U., Estimating Small Probabilities by Leaving-One-Out. In Proceedings Third European Conference on Speech Communication and Technology, pp. 2239-2242, Berlin, 1993.
• [82] Ney H., Essen U., Kneser R., On Structuring Probabilistic Dependencies in Stochastic Language Modelling. Computer Speech and Language, 8(1): 1-38, 1994 a.
• [83] Ney H., Haeb-Umbach R., Tran В. H., Oerder M., Improvements in Beam Search for 10000 Word Continuous Speech Recognition. In Proceedings ICASSP 92, pp. 9-12, San Francisco, CA, 1992.
• [84] Ney H„ Steinbiss V., Haeb-Umbach R., Tran В. H., Essen U., An Overview of the Philips Research System for Large-Vocabulary Continuous-Speech Recognition. International Journal of Pattern Recognition and Artificial Intelligence, Special Issue on Speech Recognition for Different Languages. 8(1): 33-70, 1994 b.
• [85] Odell J. J., The Use of Context in Large Vocabulary Speech Recognition. PhD thesis, Cambridge University. PhD thesis, Cambridge University, 1995.
• [86] Odell J. J., Valtchev V., Woodland P. C., Young S. J., A One- Pass Decoder Design for Large Vocabulary Recognition. In Proceedings ARPA Human Language Technology Workshop, pp. 405-410, Merrill Lynch Conference Centre. Morgan-Kaufmann Publishers Inc., San Mateo, CA, 1994.
• [87] Oppenheim A. V., Sygnały cyfrowe i ich zastosowanie . WNT, Warszawa, 1980.
• [88] Paul D. B., Speech Recognition Using Hidden Markov Models. Lancoln Laboratory Journal, 3(1): 41-62, 1990.
• [89] Paul D. B., Algorithms for an Optimal As Search and Linearizing the Search in the Stack Decoder. In Proceedings ICASSP 91, pp. 693-696. Toronto, 1991.
• [90] Pearlmutter N., MacDonald M., Plausibility and Syntactic Ambiguity Resolution. In Proceedings 14th Annual Conf, of the Cognitive Society, 1992.
• [91] Polifroni J., Seneff S., Zue V., Collection of spontaneous speech for the ATIS domain and comparative analyses of data collected at MIT and TI. In Proceedings DARPA Speech and Natural Language Workshop, 1992.
• [92] Price P. J., Bernstein W. F. J., Pallett D., A Database for Continuous Speech Recognition in a 1000 Word Domain. In Proceedings ICASSP 88, pp. 651-654, New York, 1988.
• [93] Rabiner L. R., A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proceedings of the IEEE, 77(2): 257285, 1989.
• [94] Rabiner L. R., Juang В. H., An Introduction to Hidden Markov Models. IEEE ASSP Magazine, p. 4ff, 1986.
• [95] Rabiner L. R., Juang В. H., Fundamentals of Speech Recognition. Prentice Hall, Englewood Cliffs, NJ, 1993.
• [96] Robinson T., Fransen J., Pye D., Foote J., Renals S., WSJCAMO: A British English speech corpus for large vocabulary continuous speech recognition. In Proceedings ICASSP 95, vol. 1, pp. 81-84, Detroit, 141, 1995.
• [97] Rocławski B. (1986) Poradnik fonetyczny dla nauczycieli, WSiP, Warszawa.
• [98] Rocławski B. (1998) Słownik ortograficzno - ortofoniczny, Glotispol, Gdańsk 1998.
• [99] Rocławski B. (1991) Słuch fonemowy i fonetyczny - teoria i praktyka, UG, Gdańsk 1991.
• [100] Rose R. C., Keyword detection in conversational speech utterances using hidden Markov model based continuous speech recognition. Computer Speech and Language, 9: 309-333, 1995.
• [101] Rosenfeld R., Adaptive Statistical Language Modeling: A Maximum a Entropy Approach. PhD thesis, School of Computer Science. Carnegie Mellon University, Pittsburgh, PA. Technical report CMU-CS-94-138, 1994.
• [102] Rosenfeld R., The CMU Statistical Language Modeling Toolkit for Language Modeling and its Use in the 1994 ARPA CSR Evaluation. In Proceedings Spoken Language Systems Technology Workshop, pp. 47-50, .Austin, TX. Morgan-Kaufmann Publishers Inc., San Francisco, CA, 1995.
• [103] Samaria F., Fallside F., Face Identification and Feature Extraction using Hidden Markov Models. In Vernazza, G., (ed.), Image Processing: Theory and Applications, 1. Elsevier, 1993.
• [104] Sanchis E., Casacuberta F., Galiano L, Segarra E., Learning Structural Models of Subword Units through Grammatical Inference. In IEEE ICASSP 91, vol. 1, pp. 189-192, 1991.
• [105] Schukat-Talamazzini E. G., Niemann H., ISADORA - A speech modelling network based on hidden Markov models. Computer Speech and Language, 1992.
• [106] Schwartz R. and Austin S., A Comparison of Several Approximate Algorithms For Finding Multiple (N-BEST) Sentence Hypotheses. In Proceedings ICASSP 91, pp. 701-704, Toronto, 1991.
• [107] Schwartz R., Austin S., Kubala F., Makhoul J., Nguyen L., Placeway P., Zavaliagkos G., New uses of the N-best sentence hypotheses within the Biblos speech recognition system. In Proceedings ICASSP 92, San Francisco, 1992.
• [108] Schwartz R., Chow Y. L., The V-Best Algorithm: An Efficient and Exact Procedure for Finding the N Most Likely Sentence Hypotheses. In Proceedings ICASSP 90, pp. 81-84, Albuquerque, 1990.
• [109] Smith R., Probabilistic Performance Models of Language. Mouton de Gruyter, The Hague, 1973.
• [110] Soong F. K., Huang E. F., A tree-trellis fast search for finding the N-best sentences hypotheses in continuous speech recognition. In Proceedings ICASSP 91, Toronto, 1992.
• [111] Suppes P., Probabilistic Grammars for Natural Languages. In Synthese, vol. 22, 1970.
• [112] Tadeusiewicz R., Sygnał mowy. WKiŁ, Warszawa, 1988.
• [113] Vidal E., Casacuberta F., Garcia P., Syntactic learning techniques for language modeling and acoustic phonetic decoding. In Rubio, J. and Lopez, J. M., (eds.), Speech recognition and coding: New advances and Trends. Springer-Verlag, Berlin, 1994.
• [114] Viterbi A., Error bounds for convolutional codes and an asymptotically optimum decoding algorithm, in IEEE Trans. Information Theory, vol. IT-13, pp. 260-269, 1967.
• [115] Wiśniewski A.M., Metody rozpoznawania słów izolowanych. Biuletyn IAiR WAT, nr 6, 1997.
• [116] Wiśniewski A.M., Przegląd stanu technologii rozpoznawania mowy. Biuletyn IAiR WAT, nr 7, 1997.
• [117] Wiśniewski A.M., Niejawne modele Markowa w rozpoznawaniu mowy. Biuletyn IAiR WAT, nr 7, 1997.
• [118] Wiśniewski A.M., Projekt stanowiska badawczego do przetwarzania sygnałów mowy w środowisku PC. Biuletyn IAiR WAT, nr 8, 1997.
• [119] Wiśniewski A.M., Analiza pasmowa sygnałów mowy. Biuletyn IAiR WAT, nr 8, 1997.
• [120] Wiśniewski A.M., Zasady projektowania zasobów mowy. Biuletyn IAiR WAT, nr 12, 2000.
• [121] Wright J. H., Jones G. J., Lloyd-Thomas H., A Consolidated Language Model For Speech Recognition. In Proceedings Third European Conference on Speech Communication and Technology, pp. 977-980, Berlin, 1993.
• [122] Yamron J., A Generalization of N-grams. In Proceedings DARPA Workshop on Robust Speech Recognition, Rutgers University, Piscataway, NJ, 1994.
• [123] Young S. J., Bloothooft, Corpus-Based Methods In Language and Speech Processing, Kluwer Academic Publishers, Dordrecht, Boston, London, 1997.
• [124] Young S. J., Jansen J., Odell J. J., Ollason D., Woodland P. C., The НТК Book. http://sip.uwatrloo.ca//software/HTKBook/HTKBook.html, 1997.
• [125] Young S. J., Odell J. J., Woodland P. C., Tree-Based State Tying for High Accuracy Acoustic Modelling. In Proceedings ARPA Human Language Technology Workshop. Plainsboro, NJ, pp. 286-291. Morgan-Kaufmann Publishers Inc., San Mateo, CA, 1994.
• [126] Young S. J., Russell N. H., Thornton J. H., Token Passing: A Simple Conceptual Model for Connected Speech Recognition Systems. Technical Report CUED/F-INFENG/TR38, Cambridge University Engineering Dept., 1989 a.
• [127] Young S. J., Shih H. H., Computer Assisted Grammar Construction. In Second International Colloquium ‘Grammatical Inference and Applications1, pp. 282-290, Alicante. Springer- Verlag, Berlin, 1994.
• [128] Young S. J., Woodland P. C., State clustering in hidden Markov model-based continuous speech recognition. Computer Speech and Language, 8: 369-383, 1994.