{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T00:28:22Z","timestamp":1767140902686,"version":"build-2238731810"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2005,6,1]],"date-time":"2005-06-01T00:00:00Z","timestamp":1117584000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2005,6]]},"DOI":"10.1007\/s10772-005-2166-6","type":"journal-article","created":{"date-parts":[[2006,1,6]],"date-time":"2006-01-06T17:03:14Z","timestamp":1136566994000},"page":"147-160","source":"Crossref","is-referenced-by-count":9,"title":["Aligning Text and Phonemes for Speech Technology Applications Using an EM-Like Algorithm"],"prefix":"10.1007","volume":"8","author":[{"given":"R. I.","family":"Damper","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Y.","family":"Marchand","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J.-D. S.","family":"Marsters","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A. I.","family":"Bazin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"2166_CR1","first-page":"207","volume-title":"Towards a History of Phonetics","author":"D. Abercrombie","year":"1981","unstructured":"Abercrombie, D. (1981). Extending the Roman alphabet: Some orthographic experiments of the past four centuries. In R.E. Asher and E. Henderson (Eds.), Towards a History of Phonetics. Edinburgh, UK: Edinburgh University Press, pp. 207\u2013224."},{"issue":"2","key":"2166_CR2","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1006\/csla.1998.0042","volume":"12","author":"P.C. Bagshaw","year":"1998","unstructured":"Bagshaw, P.C. (1998). Phonemic transcription by analogy in text-to-speech synthesis: Novel word pronunciation and lexicon compression. Computer Speech and Language, 12(2):119\u2013142.","journal-title":"Computer Speech and Language"},{"key":"2166_CR3","unstructured":"Baum, L.E. (1972). An inequality and associated maximization technique in statistical estimation for probabilistic functions of Markov processes. In Inequalities III: Proceedings of the Third Symposium on Inequalities, Los Angeles, CA, pp. 1\u20138."},{"key":"2166_CR4","volume-title":"Dynamic Programming","author":"R. Bellman","year":"1957","unstructured":"Bellman, R. (1957). Dynamic Programming. Princeton, NJ: Princeton University Press."},{"key":"2166_CR5","unstructured":"Black, A.W., Lenzo, K., and Pagel, V. (1998). Issues in building general letter-to-sound rules. In Proceedings of 3rd European Speech Communication Association (ESCA)\/COCOSDA International Workshop on Speech Synthesis. Jenolan Caves, Australia, pp. 77\u201380."},{"key":"2166_CR6","doi-asserted-by":"crossref","DOI":"10.4324\/9780203199916","volume-title":"A Survey of English Spelling","author":"E. Carney","year":"1994","unstructured":"Carney, E. (1994). A Survey of English Spelling. London, UK: Routledge."},{"key":"2166_CR7","volume-title":"The Sound Pattern of English","author":"N. Chomsky","year":"1968","unstructured":"Chomsky, N. and Halle, M. (1968). The Sound Pattern of English. New York, NY: Harper and Row."},{"key":"2166_CR8","first-page":"151","volume-title":"Strategies of Information Processing","author":"M. Coltheart","year":"1978","unstructured":"Coltheart, M. (1978). Lexical access in simple reading tasks. In G. Underwood (Ed.), Strategies of Information Processing. New York: Academic Press, pp. 151\u2013216."},{"key":"2166_CR9","first-page":"67","volume-title":"Orthographies and Reading: Perspectives from Cognitive Psychology, Neuropsychology and Linguistics","author":"M. Coltheart","year":"1984","unstructured":"Coltheart, M. (1984). Writing systems and reading disorders. In L. Henderson (Ed.), Orthographies and Reading: Perspectives from Cognitive Psychology, Neuropsychology and Linguistics. London, UK: Lawrence Erlbaum Associates, pp. 67\u201379."},{"key":"2166_CR10","volume-title":"Data-Driven Methods in Speech Synthesis","year":"2001","unstructured":"Damper, R.I. (Ed.) (2001). Data-Driven Methods in Speech Synthesis. Dordrecht, The Netherlands: Kluwer Academic Publishers."},{"key":"2166_CR11","doi-asserted-by":"crossref","unstructured":"Damper, R.I. and Eastmond, J.F.G. (1996). Pronouncing text by analogy. In Proceedings of 16th International Conference on Computational Linguistics. Copenhagen, Denmark, Vol 2, pp. 268\u2013273.","DOI":"10.3115\/992628.992676"},{"issue":"1","key":"2166_CR12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1177\/002383099704000101","volume":"40","author":"R.I. Damper","year":"1997","unstructured":"Damper, R.I. and Eastmond, J.F.G. (1997). Pronunciation by analogy: Impact of implementational choices on performance. Language and Speech, 40(1):1\u201323.","journal-title":"Language and Speech"},{"issue":"2","key":"2166_CR13","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1006\/csla.1998.0117","volume":"13","author":"R.I. Damper","year":"1999","unstructured":"Damper, R.I., Marchand, Y., Adamson, M.J., and Gustafson, K. (1999). Evaluating the pronunciation component of text-to-speech systems for English: A performance comparison of different approaches. Computer Speech and Language, 13(2):155\u2013176.","journal-title":"Computer Speech and Language"},{"issue":"1","key":"2166_CR14","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/0885-2308(91)90017-K","volume":"5","author":"M.J. Dedina","year":"1991","unstructured":"Dedina, M.J. and Nusbaum, H.C. (1991). Pronounce: A program for pronunciation by analogy. Computer Speech and Language, 5(1):55\u201364.","journal-title":"Computer Speech and Language"},{"issue":"1","key":"2166_CR15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"A.P. Dempster","year":"1977","unstructured":"Dempster, A.P., Laird, N.M., and Rubin, D.B. (1977). Maximum-likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, Series B, 39(1):1\u201338.","journal-title":"Journal of the Royal Statistical Society, Series B"},{"key":"2166_CR16","unstructured":"Federici, S., Pirrelli, V., and Yvon, F. (1995). Advances in analogy-based learning: False friends and exceptional items in pronunciation by paradigm-driven analogy. In Proceedings of International Joint Conference on Artificial Intelligence (IJCAI'95) Workshop on New Approaches to Learning for Natural Language Processing, Montreal, Canada, pp. 158\u2013163."},{"key":"2166_CR17","doi-asserted-by":"crossref","unstructured":"Forney, G. D. (1973). The Viterbi algorithm. In Proceedings of the IEEE, vol. 61, no. 3, pp. 268\u2013278.","DOI":"10.1109\/PROC.1973.9030"},{"key":"2166_CR18","doi-asserted-by":"crossref","first-page":"174","DOI":"10.2307\/2527783","volume":"14","author":"H. Hartley","year":"1958","unstructured":"Hartley, H. (1958). Maximum likelihood estimation from incomplete data. Biometrics 14, 174\u2013194.","journal-title":"Biometrics"},{"key":"2166_CR19","first-page":"11","volume-title":"Orthographies and Reading: Perspectives from Cognitive Psychology, Neuropsychology and Linguistics","author":"L. Henderson","year":"1984","unstructured":"Henderson, L. (1984). Writing systems and reading processes. In L. Henderson (Ed.), Orthographies and Reading: Perspectives from Cognitive Psychology, Neuropsychology and Linguistics. London, UK: Lawrence Erlbaum Associates, pp. 11\u201324."},{"key":"2166_CR20","volume-title":"Introduction to Automata Theory, Languages, and Computation","author":"J.E. Hopcroft","year":"2001","unstructured":"Hopcroft, J.E., Motwani, R., and Ullman, J.D. (2001). Introduction to Automata Theory, Languages, and Computation, 2nd ed. Boston, MA: Addison-Wesley.","edition":"2"},{"key":"2166_CR21","unstructured":"Jansche, M. (2001). Re-engineering letter to sound rules. In Second Meeting of the North American Chapter of the Association for Computational Linguistics, NAACL 2001, Pittsburg, PA. Paper N01-1015 in on-line archive at http:\/\/acl.ldc.upenn.edu\/N\/N01\/."},{"key":"2166_CR22","first-page":"85","volume-title":"Interactive Processes in Reading","author":"L. Katz","year":"1981","unstructured":"Katz, L. and Feldman, L.B. (1981). Linguistic coding in word recognition: comparisons between a deep and a shallow orthography. In A.M. Lesgold and C.A. Perfetti (Eds.), Interactive Processes in Reading. Hillsdale, NJ: Lawrence Erlbaum Associates, pp. 85\u2013106."},{"key":"2166_CR23","first-page":"27","volume":"1997","author":"K. Knill","year":"1997","unstructured":"Knill, K. and Young, S. (1997). Hidden Markov models in speech and language processing. See See Young and Bloothooft (1997), pp. 27\u201368.","journal-title":"See See Young and Bloothooft"},{"key":"2166_CR24","first-page":"11","volume-title":"Time Warps, String Edits and Macro-molecules: The Theory and Practice of Sequence Comparison","author":"J.B. Kruskal","year":"1983","unstructured":"Kruskal, J.B. (1983). An overview of sequence comparison. In D. Sankoff and J. B. Kruskal (Eds.), Time Warps, String Edits and Macro-molecules: The Theory and Practice of Sequence Comparison. Reading, MA: Addison-Wesley, pp. 11\u201344."},{"issue":"2","key":"2166_CR25","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1016\/S0885-2308(86)80020-1","volume":"1","author":"S.G.C. Lawrence","year":"1986","unstructured":"Lawrence, S.G.C. and Kaye, G. (1986). Alignment of phonemes with their corresponding orthography. Computer Speech and Language, 1(2):153\u2013165.","journal-title":"Computer Speech and Language"},{"key":"2166_CR26","first-page":"137","volume-title":"Orthography, Reading and Dyslexia","author":"I. Liberman","year":"1980","unstructured":"Liberman, I., Liberman, A., Mattingly, I. and Shankweiler, D. (1980). Orthography and the beginning reader. In J. Kavanagh and R. Venezky (Eds.), Orthography, Reading and Dyslexia. Baltimore, OH: University Park Press, pp. 137\u2013153."},{"key":"2166_CR27","doi-asserted-by":"crossref","unstructured":"Luk, R.W.P. and Damper, R.I. (1991). A novel approach to inferring letter-phoneme correspondences. In Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP'91. Toronto, Canada, Vol 2, pp. 741\u2013744.","DOI":"10.1109\/ICASSP.1991.150447"},{"key":"2166_CR28","doi-asserted-by":"crossref","unstructured":"Luk, R.W.P. and Damper, R.I. (1992). Inference of letter-phoneme correspondences by delimiting and dynamic time warping techniques. In Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP'92. San Francisco, CA, Vol 2, pp. II.61\u2013II.64.","DOI":"10.1109\/ICASSP.1992.226120"},{"key":"2166_CR29","doi-asserted-by":"crossref","unstructured":"Luk, R.W.P. and Damper, R.I. (1993). Inference of letter-phoneme correspondences with pre-defined consonant and vowel patterns. In Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP'93. Minneapolis, MN, Vol 2, pp. II.203\u2013II.206.","DOI":"10.1109\/ICASSP.1993.319269"},{"issue":"2","key":"2166_CR30","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1006\/csla.1996.0009","volume":"10","author":"R.W.P. Luk","year":"1996","unstructured":"Luk, R.W.P. and Damper, R.I. (1996). Stochastic phonographic transduction for English. Computer Speech and Language, 10(2):133\u2013153.","journal-title":"Computer Speech and Language"},{"issue":"3","key":"2166_CR31","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1109\/89.668816","volume":"6","author":"R.W.P. Luk","year":"1998","unstructured":"Luk, R.W.P. and Damper, R.I. (1998). Computational complexity of a fast Viterbi decoding algorithm for stochastic letter-phoneme transduction. IEEE Transactions on Speech and Audio Processing, 6(3):217\u2013225.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"2","key":"2166_CR32","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1162\/089120100561674","volume":"26","author":"Y. Marchand","year":"2000","unstructured":"Marchand, Y. and Damper, R.I. (2000). A multistrategy approach to improving pronunciation by analogy. Computational Linguistics, 26(2):195\u2013219.","journal-title":"Computational Linguistics"},{"issue":"3\/4","key":"2166_CR33","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1016\/0885-2308(87)90013-1","volume":"2","author":"N. McCulloch","year":"1987","unstructured":"McCulloch, N., Bedworth, M., and Bridle, J. (1987). netspeak\u2014a re-implementation of nettalk. Computer Speech and Language, 2(3\/4):289\u2013301.","journal-title":"Computer Speech and Language"},{"key":"2166_CR34","volume-title":"The EM Algorithm and Extensions","author":"G.J. McLachlan","year":"1997","unstructured":"McLachlan, G.J. and Krishnan, T. (1997). The EM Algorithm and Extensions. New York, NY: John Wiley."},{"issue":"6","key":"2166_CR35","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1109\/79.543975","volume":"13","author":"T.K. Moon","year":"1996","unstructured":"Moon, T.K. (1996). The expectation-maximization algorithm. IEEE Signal Processing Magazine, 13(6):47\u201360.","journal-title":"IEEE Signal Processing Magazine"},{"issue":"3","key":"2166_CR36","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1016\/0022-2836(70)90057-4","volume":"48","author":"S.B. Needleman","year":"1970","unstructured":"Needleman, S.B. and Wunsch, C.D. (1970). An efficient method applicable to the search for similarities in the amino acid sequences of two proteins. Journal of Molecular Biology, 48(3):444\u2013453.","journal-title":"Journal of Molecular Biology"},{"key":"2166_CR37","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1109\/TIT.1975.1055355","volume":"IT-21","author":"D.L. Neuhoff","year":"1975","unstructured":"Neuhoff, D.L. (1975). The Viterbi algorithm as an aid in text recognition. In IEEE Transactions on Information Theory, IT-21:222\u2013226.","journal-title":"IEEE Transactions on Information Theory"},{"key":"2166_CR38","unstructured":"Parfitt, S.H. and Sharman, R.A. (1991). A bidirectional model of English pronunciation. In Proceedings of 2nd European Conference on Speech Communication and Technology, Eurospeech'91. Genova, Italy, Vol 2, pp. 800\u2013804."},{"key":"2166_CR39","unstructured":"Pirrelli, V. and Federici, S. (1994). On the pronunciation of unknown words by analogy in text-to-speech systems. In Proceedings of the Second Onomastica Research Colloquium. London, UK, pp. 43\u201350."},{"key":"2166_CR40","doi-asserted-by":"crossref","unstructured":"Pirrelli, V. and Federici, S. (1995). You'd better say nothing than something wrong: Analogy, accuracy and text-to-speech applications. In Proceedings of 4th European Conference on Speech Communication and Technology, Eurospeech'95. Madrid, Spain, Vol 1, pp. 855\u2013858.","DOI":"10.21437\/Eurospeech.1995-195"},{"issue":"3","key":"2166_CR41","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1080\/095281399146472","volume":"11","author":"V. Pirrelli","year":"1999","unstructured":"Pirrelli, V. and Yvon, F. (1999). The hidden dimension: A paradigmatic view of data-driven NLP. Journal of Experimental and Theoretical Artificial Intelligence, 11(3):391\u2013408.","journal-title":"Journal of Experimental and Theoretical Artificial Intelligence"},{"issue":"5","key":"2166_CR42","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1109\/34.682181","volume":"20","author":"E.S. Ristad","year":"1998","unstructured":"Ristad, E.S. and Yianilos, P.M. (1998). Learning string-edit distance. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(5):522\u2013532.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2166_CR43","volume-title":"Writing Systems","author":"G. Sampson","year":"1985","unstructured":"Sampson, G. (1985). Writing Systems. London, UK: Hutchinson."},{"issue":"1","key":"2166_CR44","first-page":"145","volume":"1","author":"T.J. Sejnowski","year":"1987","unstructured":"Sejnowski, T.J. and Rosenberg, C.R. (1987). Parallel networks that learn to pronounce English text. Complex Systems, 1(1):145\u2013168.","journal-title":"Complex Systems"},{"key":"2166_CR45","first-page":"45","volume":"2001","author":"K.P.H. Sullivan","year":"2001","unstructured":"Sullivan, K.P.H. (2001). Analogy, the corpus and pronunciation. See Damper (2001), pp. 45\u201370.","journal-title":"See Damper"},{"issue":"3\u20134","key":"2166_CR46","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1016\/0167-6393(93)90043-K","volume":"13","author":"K.P.H. Sullivan","year":"1993","unstructured":"Sullivan, K.P.H. and Damper, R.I. (1993). Novel-word pronunciation: A cross-language study. Speech Communication, 13(3\u20134):441\u2013452.","journal-title":"Speech Communication"},{"key":"2166_CR47","first-page":"81","volume-title":"Orthographies and Reading: Perspectives from Cognitive Psychology, Neuropsychology and Linguistics","author":"M.T. Turvey","year":"1984","unstructured":"Turvey, M.T., Feldman, L.B. and Lukatela, G. (1984). The Serbo-Croatian orthography constrains the reader to a phonologically analytic strategy. In L. Henderson (Ed.) Orthographies and Reading: Perspectives from Cognitive Psychology, Neuropsychology and Linguistics. London, UK: Lawrence Erlbaum Associates, pp. 81\u201389."},{"key":"2166_CR48","volume-title":"A Study of English Spelling-to-Sound Correspondences on Historical Principles","author":"R.L. Venezky","year":"1965","unstructured":"Venezky, R.L. (1965). A Study of English Spelling-to-Sound Correspondences on Historical Principles. Ann Arbor, MI: Ann Arbor Press."},{"key":"2166_CR49","doi-asserted-by":"crossref","DOI":"10.1515\/9783110804478","volume-title":"The Structure of English Orthography","author":"R.L. Venezky","year":"1970","unstructured":"Venezky, R.L. (1970). The Structure of English Orthography. The Hague, The Netherlands: Mouton."},{"issue":"2","key":"2166_CR50","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1109\/TIT.1967.1054010","volume":"IT-13","author":"A.J. Viterbi","year":"1967","unstructured":"Viterbi, A.J. (1967). Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. IEEE Transactions on Information Theory, IT-13(2):260\u2013269.","journal-title":"IEEE Transactions on Information Theory"},{"issue":"1","key":"2166_CR51","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1214\/aos\/1176346060","volume":"11","author":"C.F.J. Wu","year":"1983","unstructured":"Wu, C.F.J. (1983). On the convergence properties of the EM algorithm. Annals of Statistics, 11(1):95\u2013103.","journal-title":"Annals of Statistics"},{"key":"2166_CR52","volume-title":"Corpus-Based Methods in Language and Speech Processing","year":"1997","unstructured":"Young, S. and G. Bloothooft (Eds.) (1997). Corpus-Based Methods in Language and Speech Processing. Dordrecht, The Netherlands: Kluwer Academic Publishers."},{"key":"2166_CR53","unstructured":"Yvon, F. (1996a). Grapheme-to-phoneme conversion using multiple unbounded overlapping chunks. In Proceedings of Conference on New Methods in Natural Language Processing (NeMLaP-2'96). Ankara, Turkey, pp. 218\u2013228."},{"key":"2166_CR54","unstructured":"Yvon, F. (1996b). Prononcer par Analogie: Motivations, Formalisations et \u00c9valuations. PhD thesis, ENST, Paris, France."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-005-2166-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-005-2166-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-005-2166-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,6]],"date-time":"2025-01-06T18:29:48Z","timestamp":1736188188000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-005-2166-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005,6]]},"references-count":54,"aliases":["10.1007\/s10971-005-2166-7"],"journal-issue":{"issue":"2","published-print":{"date-parts":[[2005,6]]}},"alternative-id":["2166"],"URL":"https:\/\/doi.org\/10.1007\/s10772-005-2166-6","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2005,6]]}}}