{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T02:22:40Z","timestamp":1783131760354,"version":"3.54.6"},"publisher-location":"Berlin, Heidelberg","reference-count":127,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540406358","type":"print"},{"value":"9783540451150","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2003]]},"DOI":"10.1007\/978-3-540-45115-0_3","type":"book-chapter","created":{"date-parts":[[2010,6,22]],"date-time":"2010-06-22T20:03:08Z","timestamp":1277236988000},"page":"38-77","source":"Crossref","is-referenced-by-count":5,"title":["A Tutorial on Pronunciation Modeling for Large Vocabulary Speech Recognition"],"prefix":"10.1007","author":[{"given":"Eric","family":"Fosler-Lussier","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"3_CR1","unstructured":"Adda, G., Lamel, L., Adda-Decker, M., Gauvain, J.L.: Language and lexical modeling in the LIMSI Nov96 Hub4 system. In: Proceedings of the DARPA Speech Recognition Workshop (February 1997)"},{"key":"3_CR2","unstructured":"Adda-Decker, M., Lamel, L.: Pronunciation variants across systems, languages, and speaking style. In: ESCA Tutorial and Research Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Kerkrade, Netherlands, pp. 1\u20136 (1998)"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Amdal, I., Korkmazskiy, F., Surendran, A.C.: Joint pronunication modelling of nonnative speakers using data-driven methods. In: Proceedings of the 5th Int\u2019l Conference on Spoken Language Processing (ICSLP-2000), Bejing, China (2000)","DOI":"10.21437\/ICSLP.2000-612"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Andersen, O., Kuhn, R., Lazarid\u00e8s, A., Dalsgaard, P., Haas, J., N\u00f6th, E.: Comparison of two tree-structured approaches for grapheme-to-phoneme conversion. In: Proceedings of the 4th Int\u2019l Conference on Spoken Language Processing (ICSLP 1996), Philadelphia, PA (October 1996)","DOI":"10.21437\/ICSLP.1996-432"},{"key":"3_CR5","volume-title":"Phonology in the Twentieth Century: Theories of Rules and Theories of Representations","author":"S. Anderson","year":"1985","unstructured":"Anderson, S.: Phonology in the Twentieth Century: Theories of Rules and Theories of Representations. University of Chicago Press, Chicago (1985)"},{"issue":"4","key":"3_CR6","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1016\/0167-6393(96)00024-6","volume":"18","author":"L. Arslan","year":"1996","unstructured":"Arslan, L., Hansen, J.: Language accent classification in American English. Speech Communication\u00a018(4), 353\u2013367 (1996)","journal-title":"Speech Communication"},{"key":"3_CR7","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/S0167-6393(99)00033-3","volume":"29","author":"M. Bacchiani","year":"1999","unstructured":"Bacchiani, M., Ostendorf, M.: Joint lexicon, model inventory, and model design. Speech Communication\u00a029, 99\u2013114 (1999)","journal-title":"Speech Communication"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Bahl, L.R., Baker, J.K., Cohen, P.S., Jelinek, F., Lewis, B.L., Mercer, R.L.: Recognition of a continuously read natural corpus. In: Proceedings IEEE Int\u2019l Conference on Acoustics, Speech, & Signal Processing (ICASSP 1978), Tulsa, pp. 422\u2013424 (1978)","DOI":"10.1109\/ICASSP.1978.1170402"},{"key":"3_CR9","volume-title":"Proceedings IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing","author":"L.R. Bahl","year":"1991","unstructured":"Bahl, L.R., Bellegarda, J.R., de Souza, P.V., Gopalakrishnan, P.S., Nahamoo, D., Picheny, M.A.: A new class of fenonic Markov word models for large vocabulary continuous speech recognition. In: Proceedings IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing, Toronto, Canada, May 1991. IEEE, Los Alamitos (1991)"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Bahl, L.R., Das, S., de Souza, P.V., Epstein, M., Mercer, R.L., Merialdo, B., Nahamoo, D., Picheny, M.A., Powell, J.: Automatic phonetic baseform determination. In: Proceedings IEEE Int\u2019l Conference on Acoustics, Speech, & Signal Processing (ICASSP 1991), vol.\u00a01, pp. 173\u2013176 (1981)","DOI":"10.1109\/ICASSP.1991.150305"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Bernstein, J., Pisoni, D.B.: Unlimited text-to-speech system: description and evaluation of a microprocessor-based device. In: Proceedings IEEE Int\u2019l Conference on Acoustics, Speech, & Signal Processing (ICASSP 1980), pp. 576\u2013579 (1980)","DOI":"10.1109\/ICASSP.1980.1170973"},{"key":"3_CR12","unstructured":"Beulen, K., Ortmanns, S., Eiden, A., Martin, S., Welling, L., Overmann, J., Ney, H.: Pronunciation modelling in the RWTH large vocabulary speech recognizer. In: Strik, H., Kessens, J.M., Wester, M. (eds.) ESCA Tutorial and Research Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Kerkrade, Netherlands, pp. 13\u201316 (April 1998)"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Boulianne, G., Brousseau, J., Ouellet, P., Dumouchel, P.: French large vocabulary recognition with cross-word phonology transducers. In: Proceedings IEEE Int\u2019l Conference on Acoustics, Speech, & Signal Processing (ICASSP 2000), Istanbul, Turkey (2000)","DOI":"10.1109\/ICASSP.2000.862072"},{"key":"3_CR14","volume-title":"Classification and Regression Trees","author":"L. Breiman","year":"1984","unstructured":"Breiman, L., Friedman, J.H., Olshen, R.A., Stone, C.J.: Classification and Regression Trees. Wadsworth, Belmont (1984)"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Brill, E.: Automatic grammar induction and parsing free text: A transformation-based approach. In: Proceedings of the 31st Meeting of the Association for Computational Linguistics (1993)","DOI":"10.3115\/981574.981609"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Chen, F.: Identification of contextual factors for pronounciation networks. In: Proceedings IEEE Int\u2019l Conference on Acoustics, Speech, & Signal Processing (ICASSP 1990), pp. 753\u2013756 (1990)","DOI":"10.1109\/ICASSP.1990.115902"},{"key":"3_CR17","volume-title":"The Sound Pattern of English","author":"N. Chomsky","year":"1968","unstructured":"Chomsky, N., Halle, M.: The Sound Pattern of English. Harper and Row, New York (1968)"},{"key":"3_CR18","unstructured":"CMU. The Carnegie Mellon Pronouncing Dictionary. Carnegie Mellon University, (1993\u2013 2002)"},{"key":"3_CR19","unstructured":"Cohen, M.H.: Phonological Structures for Speech Recognition. PhD thesis, University of California, Berkeley (1989)"},{"key":"3_CR20","volume-title":"Speech Recognition","author":"P.S. Cohen","year":"1975","unstructured":"Cohen, P.S., Mercer, R.L.: The phonological component of an automatic speechrecognition system. In: Reddy, R. (ed.) Speech Recognition. Academic Press, London (1975)"},{"key":"3_CR21","unstructured":"The ONOMASTICA Consortium. The ONOMASTICA interlanguage pronunciation lexicon. In: 4th European Conference on Speech Communication and Technology (Eurospeech 1995), pp. 829\u2013832, Madrid, Spain (September 1995)"},{"key":"3_CR22","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/S0167-6393(99)00034-5","volume":"29","author":"N. Cremelie","year":"1999","unstructured":"Cremelie, N., Martens, J.-P.: In search for better pronunciaiton models for speech recognition. Speech Communication\u00a029, 115\u2013136 (1999)","journal-title":"Speech Communication"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"De Mori, R., Snow, C., Galler, M.: On the use of stochastic inference networks for representing multiple word pronunciations. In: Proceedings IEEE Int\u2019l Conference on Acoustics, Speech, & Signal Processing (ICASSP 1995), Detroit, Michigan, pp. 568\u2013571 (1995)","DOI":"10.1109\/ICASSP.1995.479661"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Deng, L.: Integrated-multilingual speech recognition using universal phonological features in a functional speech production model. In: Proceedings IEEE Int\u2019l Conference on Acoustics, Speech, & Signal Processing (ICASSP 1997), Munich, Germany (1997)","DOI":"10.1109\/ICASSP.1997.596110"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Deshmukh, N., Ngan, J., Hamaker, J., Picone, J.: An advanced system to generate pronunciations of proper nouns. In: Proceedings IEEE Int\u2019l Conference on Acoustics, Speech, & Signal Processing (ICASSP 1997), Munich, Germany (1997)","DOI":"10.1109\/ICASSP.1997.596226"},{"key":"3_CR26","volume-title":"DARPA Broadcast News Workshop","author":"E. Eide","year":"1999","unstructured":"Eide, E.: Automatic modeling of pronunciation variations. In: DARPA Broadcast News Workshop, Herndon, Virginia (March 1999)"},{"key":"3_CR27","unstructured":"Finke, M.: The JanusRTK Switchboard\/CallHome system: Pronunciation modeling. In: Proceedings of the LVCSR Hub 5 Workshop (1996)"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Finke, M., Fritsch, J., Koll, D., Waibel, A.: Modeling and efficient decoding of large vocabulary conversational speech. In: 6th European Conference on Speech Communication and Technology (Eurospeech 1999), Budapest, Hungary (September 1999)","DOI":"10.21437\/Eurospeech.1999-120"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Finke, M., Waibel, A.: Speaking mode dependent pronunciation modeling in large vocabulary conversational speech recognition. In: 5th European Conference on Speech Communication and Technology (Eurospeech 1997) (1997)","DOI":"10.21437\/Eurospeech.1997-625"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Fitt, S.: Morphological approaches for an English pronunciation lexicon. In: Proceedings of Eurospeech, Aalborg, Denmark (2001)","DOI":"10.21437\/Eurospeech.2001-230"},{"key":"3_CR31","volume-title":"International Congress of Phonetic Sciences","author":"E. Fosler-Lussier","year":"1999","unstructured":"Fosler-Lussier, E., Greenberg, S., Morgan, N.: Incorporating contextual phonetics into automatic speech recognition. In: International Congress of Phonetic Sciences, San Francisco, California (August 1999)"},{"key":"3_CR32","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/S0167-6393(99)00035-7","volume":"29","author":"E. Fosler-Lussier","year":"1999","unstructured":"Fosler-Lussier, E., Morgan, N.: Effects of speaking rate and word frequency on pronunciations in conversational speech. Speech Communication\u00a029, 137\u2013158 (1999)","journal-title":"Speech Communication"},{"key":"3_CR33","unstructured":"Fosler-Lussier, E., Williams, G.: Not just what, but also when: Guided automatic pronunciation modeling for broadcast news. In: DARPA Broadcast News Workshop, Herndon, Virginia (March 1999)"},{"key":"3_CR34","unstructured":"Fosler-Lussier, J.E.: Dynamic Pronunciation Models for Automatic Speech Recognition. PhD thesis, University of California, Berkeley (1999)"},{"issue":"1","key":"3_CR35","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1109\/TASSP.1975.1162638","volume":"23","author":"J. Friedman","year":"1975","unstructured":"Friedman, J.: Computer exploration of fast-speech rules. IEEE Transactions on Acoustics, Speech, and Signal Processing, ASSP\u00a023(1), 100\u2013103 (1975)","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing, ASSP"},{"key":"3_CR36","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/S0167-6393(98)00066-1","volume":"27","author":"T. Fukada","year":"1999","unstructured":"Fukada, T., Yoshimura, T., Sagisaka, Y.: Automatic generation of multiple pronunciations based on neural networks. Speech Communication\u00a027, 63\u201373 (1999)","journal-title":"Speech Communication"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Garofolo, J., Lamel, L., Fisher, W., Fiscus, J., Pallett, D., Dahlgren, N.: DARPA TIMIT acoustic-phonetic continuous speech corpus. Technical Report NISTIR 4930, National Institute of Standards and Technology, Gaithersburg, MD, February 1993. Speech Data published on CD-ROM: NIST Speech Disc 1-1.1 (October 1990)","DOI":"10.6028\/NIST.IR.4930"},{"key":"3_CR38","volume-title":"Handbook of Standards and Resources for Spoken Language Systems: Spoken Language Reference Materials","year":"1998","unstructured":"Gibbon, D., Moore, R., Winski, R. (eds.): Handbook of Standards and Resources for Spoken Language Systems: Spoken Language Reference Materials, vol.\u00a04. Mouton de Gruyter, Berlin (1998)"},{"issue":"4","key":"3_CR39","first-page":"497","volume":"22","author":"D. Gildea","year":"1996","unstructured":"Gildea, D., Jurafsky, D.: Learning bias and phonological-rule induction. Computational Linguistics\u00a022(4), 497\u2013530 (1996)","journal-title":"Computational Linguistics"},{"key":"3_CR40","unstructured":"Hieronymous, J.: ASCII phonetic symbols for the world\u2019s languages: Worldbet. Journal of the International Phonetic Association (1993)"},{"key":"3_CR41","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/S0167-6393(99)00036-9","volume":"29","author":"T. Holter","year":"1999","unstructured":"Holter, T., Svendsen, T.: Maximum likelihood modelling of pronunciation variation. Speech Communication\u00a029, 177\u2013191 (1999)","journal-title":"Speech Communication"},{"key":"3_CR42","unstructured":"Humphries, J.J.: Accent Modelling and Adaptation in Automatic Speech Recognition. PhD thesis, Trinity Hall, University of Cambridge, Camridge, England (October 1997)"},{"key":"3_CR43","doi-asserted-by":"crossref","unstructured":"Imai, T., Ando, A., Miyasaka, E.: A new method for automatic generation of speakerdependent phonological rules. In: Proceedings IEEE Int\u2019l Conference on Acoustics, Speech, & Signal Processing (ICASSP 1995), vol.\u00a06, pp. 864\u2013867 (1995)","DOI":"10.1109\/ICASSP.1995.479831"},{"key":"3_CR44","unstructured":"Jakobson, R.: Observations sur le classment phonologique des consonnes. In: Proceedings of the 3rd International Congress of Phonetic Sciences, pp. 34\u201341 (1939)"},{"key":"3_CR45","series-title":"Language, Speech and Communcation Series","volume-title":"Statistical Methods for Speech Processing","author":"F. Jelinek","year":"1997","unstructured":"Jelinek, F.: Statistical Methods for Speech Processing. Language, Speech and Communcation Series. MIT Press, Cambridge (1997)"},{"key":"3_CR46","doi-asserted-by":"crossref","unstructured":"Jiang, J., Hon, H.-W., Huang, X.: Improvements on a trainable letter-to-sound converter. In: 5th European Conference on Speech Communication and Technology (Eurospeech 1997), Rhodes, Greece (1997)","DOI":"10.21437\/Eurospeech.1997-220"},{"key":"#cr-split#-3_CR47.1","doi-asserted-by":"crossref","unstructured":"Johnson, C.D.: Formal Aspects of Phonological Description, Mouton, The Hague (1972);","DOI":"10.1515\/9783110876000"},{"key":"#cr-split#-3_CR47.2","unstructured":"Monographs on Linguistic Analysis No. 3"},{"key":"3_CR48","doi-asserted-by":"crossref","unstructured":"Jordan, M.I.: A statistical approach to decision tree modeling. In: International Conference on Machine Learning, pp. 363\u2013370 (1994)","DOI":"10.1145\/180139.175372"},{"key":"3_CR49","volume-title":"Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition","author":"D. Jurafsky","year":"2000","unstructured":"Jurafsky, D., Martin, J.: Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. Prentice Hall, Upper Saddle River (2000)"},{"key":"3_CR50","doi-asserted-by":"crossref","unstructured":"Jurafsky, D., Wooters, C., Tajchman, G., Segal, J., Stolcke, A., Fosler, E., Morgan, N.: The Berkeley restaurant project. In: Proceedings of the 3rd Int\u2019l Conference on Spoken Language Processing (ICSLP 1994), Yokohama, Japan, pp. 2139\u20132142 (1994)","DOI":"10.21437\/ICSLP.1994-537"},{"key":"3_CR51","volume-title":"Connected Speech: the Interaction of Syntax and Phonology","author":"E. Kaisse","year":"1985","unstructured":"Kaisse, E.: Connected Speech: the Interaction of Syntax and Phonology. Academic Press, London (1985)"},{"key":"3_CR52","unstructured":"Kaplan, R.M., Kay, M.: Phonological rules and finite-state transducers. Paper presented at the annual meeting of the Linguistics Society of America, New York (1981)"},{"issue":"3","key":"3_CR53","first-page":"331","volume":"20","author":"R.M. Kaplan","year":"1994","unstructured":"Kaplan, R.M., Kay, M.: Regular models of phonological rule systems. Computational Linguistics\u00a020(3), 331\u2013378 (1994)","journal-title":"Computational Linguistics"},{"key":"3_CR54","first-page":"173","volume-title":"The Last Phonological Rule","author":"L. Karttunen","year":"1993","unstructured":"Karttunen, L.: Finite state constraints. In: Goldsmith, J. (ed.) The Last Phonological Rule, ch. 6, pp. 173\u2013194. University of Chicago Press, Chicago (1993)"},{"key":"3_CR55","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1006\/csla.2000.0148","volume":"14","author":"S. King","year":"2000","unstructured":"King, S., Taylor, P.: Detection of phonological features in continuous speech using neural networks. Computer Speech and Language\u00a014, 333\u2013353 (2000)","journal-title":"Computer Speech and Language"},{"key":"3_CR56","doi-asserted-by":"crossref","unstructured":"Kirchhoff, K.: Combining articulatory and acoustic information for speech recognition in noisy and reverberant environments. In: Proceedings of the 5th Int\u2019l Conference on Spoken Language Processing (ICSLP 1998), Sydney, Austrailia (1998)","DOI":"10.21437\/ICSLP.1998-313"},{"key":"3_CR57","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1121\/1.395275","volume":"3","author":"D. Klatt","year":"1987","unstructured":"Klatt, D.: A review of text-to-speech conversion for English. Journal of the Acoustical Society of America\u00a03, 737\u2013793 (1987)","journal-title":"Journal of the Acoustical Society of America"},{"key":"3_CR58","doi-asserted-by":"crossref","unstructured":"Koskenniemi, K.: Two-level morphology: A general computational model of word-form recognition and production. Technical Report Publication No. 11, Department of General Linguistics, University of Helsinki (1983)","DOI":"10.3115\/980491.980529"},{"key":"3_CR59","doi-asserted-by":"crossref","unstructured":"Kuhn, R., Junqua, J.-C., Martzen, P.D.: Rescoring multiple pronunciations generated from spelled words. In: Proceedings of the 5th Int\u2019l Conference on Spoken Language Processing (ICSLP 1998), Sydney, Austrailia (1998)","DOI":"10.21437\/ICSLP.1998-776"},{"key":"3_CR60","unstructured":"Ladefoged, P.: A Course in Phonetics, 3rd edn. Harcourt Brace Jovanovich, Inc. (1993)"},{"key":"3_CR61","doi-asserted-by":"crossref","unstructured":"Lamel, L., Adda, G.: On designing pronunciation lexicons for large vocabulary, continuous speech recognition. In: Proceedings of the 4th Int\u2019l Conference on Spoken Language Processing (ICSLP 1996) (1996)","DOI":"10.1109\/ICSLP.1996.606916"},{"issue":"8","key":"3_CR62","first-page":"707","volume":"10","author":"V.I. Levenshtein","year":"1966","unstructured":"Levenshtein, V.I.: Binary codes capable of correcting deletions, insertions, and reverslal. Cybernetics and Control Theory\u00a010(8), 707\u2013710 (1966)","journal-title":"Cybernetics and Control Theory"},{"key":"#cr-split#-3_CR63.1","unstructured":"Linguistic Data Consortium (LDC). The PRONLEX pronunciation dictionary (1996);"},{"key":"#cr-split#-3_CR63.2","unstructured":"Part of the COMPLEX distribuiton, Available from the LDC, ldc@unagi.cis.upenn.edu"},{"key":"3_CR64","doi-asserted-by":"crossref","unstructured":"Livescu, K., Glass, J.: Lexical modeling of non-native speech for automatic speech recognition. In: Proceedings of the 5th Int\u2019l Conference on Spoken Language Processing (ICSLP 2000), Istanbul, Turkey (2000)","DOI":"10.1109\/ICASSP.2000.862074"},{"key":"3_CR65","first-page":"340","volume-title":"Trends in Speech Recognition","author":"B. Lowerre","year":"1980","unstructured":"Lowerre, B., Reddy, R.: The HARPY speech recognition system. In: Lea, W.A. (ed.) Trends in Speech Recognition, ch. 15, pp. 340\u2013360. Prentice Hall, Englewood Cliffs (1980)"},{"key":"3_CR66","doi-asserted-by":"crossref","unstructured":"Lucassen, J.M., Mercer, R.L.: An information theoretic approach to the automatic determination of phonemic baseforms. In: Proceedings IEEE Int\u2019l Conference on Acoustics, Speech, & Signal Processing (ICASSP 1984) (1984)","DOI":"10.1109\/ICASSP.1984.1172810"},{"key":"3_CR67","doi-asserted-by":"crossref","unstructured":"Ma, K., Zavaliagkos, G., Iyer, R.: Pronunciaion modeling for large vocabulary conversational speech recognition. In: Proceedings of the 5th Int\u2019l Conference on Spoken Language Processing (ICSLP 1998), Sydney, Australia (December 1998)","DOI":"10.21437\/ICSLP.1998-655"},{"key":"3_CR68","doi-asserted-by":"crossref","unstructured":"McAllaster, D., Gillick, L., Scattone, F., Newman, M.: Fabricating conversational speech data with acoustic models: A program to examine model-data mismatch. In: Proceedings of the 5th Int\u2019l Conference on Spoken Language Processing (ICSLP 1998), Sydney, Australia, pp. 1847\u20131850 (December 1998)","DOI":"10.21437\/ICSLP.1998-630"},{"key":"3_CR69","doi-asserted-by":"crossref","unstructured":"McCandless, M.K., Glass, J.R.: Empirical acquisition of word and phrase classes in the ATIS domain. In: 3rd European Conference on Speech Communication and Technology (Eurospeech 1993), Berlin, Germany, vol.\u00a02, pp. 981\u2013984 (1993)","DOI":"10.21437\/Eurospeech.1993-231"},{"key":"3_CR70","doi-asserted-by":"crossref","unstructured":"Mirghafori, N., Fosler, E., Morgan, N.: Fast speakers in large vocabulary continuous speech recognition: Analysis & antidotes. In: 4th European Conference on Speech Communication and Technology (Eurospeech 1995) (1995)","DOI":"10.21437\/Eurospeech.1995-131"},{"key":"3_CR71","doi-asserted-by":"crossref","unstructured":"Mohri, M., Riley, M.: Integrated context-dependent networks in very large vocabulary speech recognition. In: 6th European Conference on Speech Communication and Technology (Eurospeech 1999), Budapest, Hungary (1999)","DOI":"10.21437\/Eurospeech.1999-197"},{"key":"3_CR72","unstructured":"Mohri, M., Riley, M., Hindle, D., Ljolje, A., Pereira, F.: Full expansion of contextdependent networks in large vocabulary speech recognition. In: Proceedings of the 5th Int\u2019l Conference on Spoken Language Processing (ICSLP 1998), Sydney, Austrailia (December 1998)"},{"key":"3_CR73","unstructured":"Mokbel, H., Jouvet, D.: Derivation of the optimal phonetic transcription set for a word from its acoustic realisations. In: ESCA Tutorial and Research Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Kerkrade, Netherlands, pp. 73\u201378 (1998)"},{"key":"3_CR74","doi-asserted-by":"crossref","unstructured":"Mou, X., Seneff, S., Zue, V.: Context-dependent pobabilistic hierarchical sub-lexical modelling using finite state transducers. In: 7th European Conference on Speech Communication and Technology (Eurospeech 2001), Aalborg, Denmark (2001)","DOI":"10.21437\/Eurospeech.2001-120"},{"key":"3_CR75","unstructured":"Nock, H.J., Young, S.J.: Detecting and correcting poor pronunciations for multiword units. In: Strik, H., Kessens, J.M., Wester, M. (eds.) ESCA Tutorial and Research Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Kerkrade, Netherlands, pp. 85\u201390 (April 1998)"},{"key":"3_CR76","volume-title":"The use of decision trees with context sensitive phoneme modeling. Master\u2019s thesis","author":"J.J. Odell","year":"1992","unstructured":"Odell, J.J.: The use of decision trees with context sensitive phoneme modeling. Master\u2019s thesis. Cambridge University, Cambridge (1992)"},{"key":"3_CR77","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1016\/S0095-4470(19)30399-7","volume":"18","author":"J.J. Ohala","year":"1990","unstructured":"Ohala, J.J.: There is no interface between phonetics and phonology: A personal view. Journal of Phonetics\u00a018, 153\u2013171 (1990)","journal-title":"Journal of Phonetics"},{"key":"3_CR78","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1109\/34.211465","volume":"15","author":"J. Oncina","year":"1993","unstructured":"Oncina, J., Garc\u00eda, P., Vidal, E.: Learning subsequential transducers for pattern recognition tasks. IEEE Transcations on Pattern Analysis and Machine Intelligence\u00a015, 448\u2013458 (1993)","journal-title":"IEEE Transcations on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"3_CR79","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1109\/TASSP.1975.1162639","volume":"23","author":"B. Oshika","year":"1975","unstructured":"Oshika, B., Zue, V., Weeks, R.V., Neu, H., Aurbach, J.: The role of phonological rules in speech understanding research. IEEE Transactions on Acoustics, Speech, and Signal Processing, ASSP\u00a023(1), 104\u2013112 (1975)","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing, ASSP"},{"key":"3_CR80","unstructured":"Ostendorf, M.: Moving beyound the \u2018beads-on-a-string\u2019 model of speech. In: 1999 IEEE Workshop on Automatic Speech Recognition and Understanding, Keystone, Colorado (December 1999)"},{"key":"3_CR81","series-title":"ch. 4. Center for Language and Speech Processing","volume-title":"1996 LVCSR Summer Research Workshop Technical Reports","author":"M. Ostendorf","year":"1997","unstructured":"Ostendorf, M., Byrne, B., Bacchiani, M., Finke, M., Gunawardana, A., Ross, K., Roweis, S., Shriberg, E., Talkin, D., Waibel, A., Wheatley, B., Zeppenfeld, T.: Modeling systematic variations in pronunciation via a language-dependent hidden speaking mode. In: Jelinek, F. (ed.) 1996 LVCSR Summer Research Workshop Technical Reports, ch. 4. Center for Language and Speech Processing. Johns Hopkins University, Baltimore (April 1997)"},{"key":"3_CR82","doi-asserted-by":"crossref","unstructured":"Della Pietra, S., Della Pietra, V., Mercer, R.K., Roukos, S.: Adaptive language modeling using minimum discriminant estimation. In: Proceeding of the Speech and Natural Language DARPA Workshop (February 1992)","DOI":"10.3115\/1075527.1075551"},{"key":"3_CR83","unstructured":"Placeway, P., Chen, S., Eskenazi, M., Jain, U., Parikh, V., Raj, B., Ravishankar, M., Rosenfeld, R., Seymore, K., Siegler, M., Stern, R., Thayer, E.: The 1996 Hub-4 Sphinx-3 system. In: DARPA Speech Recognition Workshop, Chantilly, VA (February 1997)"},{"key":"3_CR84","first-page":"651","volume-title":"Proceedings IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing","author":"P. Price","year":"1988","unstructured":"Price, P., Fisher, W., Bernstein, J., Pallet, D.: The DARPA 1000-word Resource Management database for ontinuous speech recognition. In: Proceedings IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing, New York, vol.\u00a01, pp. 651\u2013654. IEEE, Los Alamitos (1988)"},{"key":"3_CR85","series-title":"Prentice Hall Signal Processing Series","volume-title":"Fundamentals of Speech Recognition","author":"L. Rabiner","year":"1993","unstructured":"Rabiner, L., Juang, B.-H.: Fundamentals of Speech Recognition. Prentice Hall Signal Processing Series. Prentice Hall, Englewood Cliffs (1993)"},{"key":"3_CR86","doi-asserted-by":"crossref","unstructured":"Randolph, M.A.: A data-driven method for discovering and predicting allophonic variation. In: Proceedings IEEE Int\u2019l Conference on Acoustics, Speech, & Signal Processing (ICASSP 1990), Albuquerque, New Mexico, vol.\u00a02, pp. 1177\u20131180 (1990)","DOI":"10.1109\/ICASSP.1990.116176"},{"key":"3_CR87","unstructured":"Ries, K., Bu\u00f8, F.D., Wang, Y.-Y.: Towards better language modeling in spontaneous speech. In: Proceedings IEEE Int\u2019l Conference on Acoustics, Speech, & Signal Processing (ICASSP 1995), Yokohama, Japan (1995)"},{"key":"3_CR88","doi-asserted-by":"crossref","unstructured":"Riley, M.: A statistical model for generating pronunciation networks. In: Proceedings IEEE Int\u2019l Conference on Acoustics, Speech, & Signal Processing (ICASSP 1991), pp. 737\u2013740 (1991)","DOI":"10.1109\/ICASSP.1991.150446"},{"key":"3_CR89","unstructured":"Riley, M., Byrne, W., Finke, M., Khudanpur, S., Ljolje, A., McDonough, J., Nock, H., Saraclar, M., Wooters, C., Zavaliagkos, G.: Stochastic pronunciation modelling from handlabelled phonetic corpora. In: ESCA Tutorial and Research Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Kerkrade, Netherlands, pp. 109\u2013116 (April 1998)"},{"key":"3_CR90","volume-title":"Automatic Speech and Speaker Recognition: Advanced Topics","author":"M.D. Riley","year":"1995","unstructured":"Riley, M.D., Ljolje, A.: Automatic generation of detailed pronunciation lexicons. In: Automatic Speech and Speaker Recognition: Advanced Topics. Kluwer Academic Publishers, Dordrecht (1995)"},{"key":"3_CR91","volume-title":"The British English Example Pronunciation Dictionary","author":"A. Robinson","year":"1994","unstructured":"Robinson, A.: The British English Example Pronunciation Dictionary, vol.\u00a01. Cambridge University, Cambridge (1994)"},{"key":"3_CR92","volume-title":"Artificial Intelligence: A Modern Approach","author":"S. Russell","year":"1995","unstructured":"Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach. Prentice Hall, Englewood Cliffs (1995)"},{"key":"3_CR93","unstructured":"Sankoff, D., Kruskal, J.: Time warps, string edits and macromolecules. CSLI Publications, Stanford, reissue edn. (1999)"},{"key":"3_CR94","unstructured":"Sara\u00e7lar, M., Khudanpur, S.: Pronunciation ambiguity vs. pronunciation variability in speech recognition. In: Proceedings IEEE Int\u2019l Conference on Acoustics, Speech, & Signal Processing (ICASSP-2000), Istanbul, Turkey (2000)"},{"key":"3_CR95","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1006\/csla.2000.0140","volume":"14","author":"M. Sarac\u00b8lar","year":"2000","unstructured":"Sarac\u00b8lar, M., Nock, H., Khudanpur, S.: Pronunciation modeling by sharing Gaussian densities across phonetic models. Computer Speech and Language\u00a014, 137\u2013160 (2000)","journal-title":"Computer Speech and Language"},{"key":"3_CR96","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/0167-6393(93)90026-H","volume":"13","author":"F. Schiel","year":"1993","unstructured":"Schiel, F.: A new approach to speaker adaptation by modelling pronunciation in automatic speech recognition. Speech Communication\u00a013, 281\u2013286 (1993)","journal-title":"Speech Communication"},{"key":"3_CR97","unstructured":"Schiel, F., Kipp, A., Tillmann, H.G.: Statistical modelling of pronunciation: it\u2019s not the model, it\u2019s the data. In: Strik, H., Kessens, J.M., Wester, M. (eds.) ESCA Tutorial and Research Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Kerkrade, Netherlands, pp. 131\u2013136 (April 1998)"},{"key":"3_CR98","doi-asserted-by":"crossref","unstructured":"Schmid, P., Cole, R., Fanty, M.: Automatically generated word pronunciations from phoneme classifier output. In: Proceedings IEEE Int\u2019l Conference on Acoustics, Speech, & Signal Processing (ICASSP 1993), vol.\u00a02, pp. 223\u2013226 (1987)","DOI":"10.1109\/ICASSP.1993.319275"},{"key":"3_CR99","unstructured":"Schramm, H., Aubert, X.: Efficient intregration of multiple pronunciations in a large vocabulary decoder. In: Proceedings IEEE Int\u2019l Conference on Acoustics, Speech, & Signal Processing (ICASSP 2000), Istanbul, Turkey (2000)"},{"key":"3_CR100","first-page":"145","volume":"1","author":"T.J. Sejnowski","year":"1987","unstructured":"Sejnowski, T.J., Rosenberg, C.R.: Parallel networks that learn to pronounce English text. Complex Systems\u00a01, 145\u2013168 (1987)","journal-title":"Complex Systems"},{"key":"3_CR101","doi-asserted-by":"crossref","unstructured":"Siegler, M.A., Stern, R.M.: On the effects of speech rate in large vocabulary speech recognition systems. In: Proceedings IEEE Int\u2019l Conference on Acoustics, Speech, & Signal Processing (ICASSP 1995) (1995)","DOI":"10.1109\/ICASSP.1995.479672"},{"key":"3_CR102","doi-asserted-by":"crossref","unstructured":"Sloboda, T., Waibel, A.: Dictionary learning for spontaneous speech recognition. In: Proceedings of the 4th Int\u2019l Conference on Spoken Language Processing, ICSLP 1996 (1996)","DOI":"10.1109\/ICSLP.1996.607274"},{"key":"3_CR103","doi-asserted-by":"crossref","unstructured":"Sproat, R., Riley, M.: Compilation of weighted finite-state transducers from decision trees. In: Proceedings of the 34th Meeting of the Association for Computational Linguistics, Santa Cruz, CA, pp. 215\u2013222 (1996)","DOI":"10.3115\/981863.981892"},{"key":"3_CR104","unstructured":"Stolcke, A., Bratt, H., Butzberger, J., Franco, J., Rao Gadde, C.R., Plauch\u00e9, M., Richey, C., Shriberg, E., S\u00f6nmez, K., Weng, F., Zheng, J.: The SRI March 2000 Hub-5 conversational speech transcription system. In: Proc. NIST Speech Transcription Workshop, College Park, Maryland (2000)"},{"key":"3_CR105","unstructured":"Strik, H.: Pronunciation adaptation at the lexical level. In: Juncqua, J.-C., Wellekens, C. (eds.) ISCA Tutorial and Research Workshop on Adaptation Methods For Speech Recognition, Sophia-Antipolis, France, pp. 123\u2013131 (August 2001)"},{"key":"3_CR106","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1016\/S0167-6393(99)00038-2","volume":"29","author":"H. Strik","year":"1999","unstructured":"Strik, H., Cucchiarini, C.: Modeling pronunciation variation for ASR: A survey of the literature. Speech Communication\u00a029, 225\u2013246 (1999)","journal-title":"Speech Communication"},{"key":"3_CR107","doi-asserted-by":"crossref","unstructured":"Tajchman, G., Fosler, E., Jurafsky, D.: Building multiple pronunciation models for novel words using exploratory computational phonology. In: 4th European Conference on Speech Communication and Technology (Eurospeech 1995), Madrid, Spain (September 1995)","DOI":"10.21437\/Eurospeech.1995-350"},{"key":"3_CR108","doi-asserted-by":"crossref","unstructured":"Tajchman, G., Jurafsky, D., Fosler, E.: Learning phonological rule probabilities from speech corpora with exploratory computational phonology. In: Proceedings of the 33 rd Meeting of the Association for Computational Linguistics (1995)","DOI":"10.3115\/981658.981659"},{"key":"3_CR109","doi-asserted-by":"crossref","unstructured":"Mayfield Tomokiyo, L.: Lexical and acoustic modeling of non-native speech in lvcsr. In: Proceedings of the 5th Int\u2019l Conference on Spoken Language Processing (ICSLP 2000), Bejing, China (2000)","DOI":"10.21437\/ICSLP.2000-821"},{"key":"3_CR110","series-title":"ch. 3. Center for Language and Speech Processing","volume-title":"1996 LVCSR Summer Research Workshop Technical Reports","author":"M. Weintraub","year":"1997","unstructured":"Weintraub, M., Fosler, E., Galles, C., Kao, Y.-H., Khudanpur, S., Saraclar, M., Wegmann, S.: WS96 project report: Automatic learning of word pronunciation from data. In: Jelinek, F. (ed.) 1996 LVCSR Summer Research Workshop Technical Reports, ch. 3. Center for Language and Speech Processing, Johns Hopkins University, Baltimore (April 1997)"},{"key":"3_CR111","unstructured":"Weintraub, M., Murveit, H., Cohen, M., Price, P., Bernstein, J., Baldwin, G., Bell, D.: Linguistic constraints in hidden Markov model based speech recognition. In: Proceedings IEEE Int\u2019l Conference on Acoustics, Speech, & Signal Processing (ICASSP 1989), pp. 651\u2013654 (1988)"},{"key":"3_CR112","unstructured":"Wells, J., et al.: Sampa computer readable phonetic alphabet (2002), http:\/\/www.phon.ucl.ac.uk\/home\/sampa\/home.htm"},{"key":"3_CR113","doi-asserted-by":"crossref","unstructured":"Westendorf, C.-M., Jelitto, J.: Learning pronunciation dictionary from speech data. In: Proceedings of the 4th Int\u2019l Conference on Spoken Language Processing, ICSLP 1996 (1996)","DOI":"10.1109\/ICSLP.1996.607784"},{"key":"3_CR114","doi-asserted-by":"crossref","unstructured":"Wester, M., Fosler-Lussier, E.: A comparison of data-derived and knowledge-based modeling of pronunciation variation. In: Proceedings of the 5th Int\u2019l Conference on Spoken Language Processing (ICSLP 2000), Bejing, China (2000)","DOI":"10.21437\/ICSLP.2000-67"},{"key":"3_CR115","doi-asserted-by":"crossref","unstructured":"Wester, M., Kessens, J., Strik, H.: Modeling pronunciation variation for a Dutch CSR: Testing three methods. In: Proceedings of the 5th Int\u2019l Conference on Spoken Language Processing (ICSLP 1998), Sydney, Australia (December 1998)","DOI":"10.21437\/ICSLP.1998-675"},{"key":"3_CR116","unstructured":"Arthur, D., Williams, G.: Knowing what you don\u2019t know: roles for confidence measures in automatic speech recognition. PhD thesis, University of Sheffield, Sheffield, England (1999)"},{"key":"3_CR117","first-page":"316","volume-title":"Trends in Speech Recognition","author":"J.J. Wolf","year":"1980","unstructured":"Wolf, J.J., Woods, W.A.: The HWIM speech understanding system. In: Lea, W.A. (ed.) Trends in Speech Recognition, ch. 14, pp. 316\u2013339. Prentice Hall, Englewood Cliffs (1980)"},{"key":"3_CR118","doi-asserted-by":"crossref","unstructured":"Wooters, C., Stolcke, A.: Multiple-pronunciation lexical modeling in a speaker independent speech understanding system. In: Proceedings of the 3rd Int\u2019l Conference on Spoken Language Processing, ICSLP 1994 (1994)","DOI":"10.21437\/ICSLP.1994-355"},{"key":"3_CR119","unstructured":"Wooters, C.C.: Lexical modeling in a speaker independent speech understanding system. PhD thesis, University of California, Berkeley, International Computer Science Institute Technical Report TR-93-068 (1993)"},{"key":"3_CR120","doi-asserted-by":"crossref","unstructured":"Yang, Q., Martens, J.-P.: Data-driven lexical modeling of pronunciation variations for ASR. In: Proceedings of the 5th Int\u2019l Conference on Spoken Language Processing (ICSLP 2000), Bejing, China (2000)","DOI":"10.21437\/ICSLP.2000-103"},{"key":"3_CR121","doi-asserted-by":"crossref","unstructured":"Young, S.J., Odell, J.J., Woodland, P.C.: Tree-based state tying for high accuracy acoustic modelling. In: Proceedings IEEE Int\u2019l Conference on Acoustics, Speech, & Signal Processing (ICASSP 1994), pp. 307\u2013312 (1994)","DOI":"10.3115\/1075812.1075885"},{"key":"3_CR122","doi-asserted-by":"crossref","unstructured":"Zheng, J., Franco, H., Weng, F., Sankar, A., Bratt, H.: Word-level rate of speech modeling using rate-specific phones and pronunciations. In: Proceedings IEEE Int\u2019l Conference on Acoustics, Speech, & Signal Processing (ICASSP 2000), Istanbul, Turkey (2000)","DOI":"10.1109\/ICASSP.2000.862097"},{"issue":"3","key":"3_CR123","first-page":"323","volume":"1","author":"A. Zwicky","year":"1970","unstructured":"Zwicky, A.: Auxiliary Reduction in English. Linguistic Inquiry\u00a01(3), 323\u2013336 (1970)","journal-title":"Linguistic Inquiry"},{"key":"3_CR124","unstructured":"Zwicky, A.: Note on a phonological hierarchy in English. In: Stockwell, R., Macaulay, R. (eds.) Linguistic Change and Generative Theory, Indiana University Press (1972)"},{"key":"3_CR125","unstructured":"Zwicky, A.: On Casual Speech. In: Eighth Regional Meeting of the Chicago Linguistic Society, pp. 607\u2013615 (April 1972)"}],"container-title":["Lecture Notes in Computer Science","Text- and Speech-Triggered Information Access"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-45115-0_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T04:56:54Z","timestamp":1740200214000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-45115-0_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003]]},"ISBN":["9783540406358","9783540451150"],"references-count":127,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-45115-0_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2003]]}}}