{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T09:29:16Z","timestamp":1748338156286},"reference-count":32,"publisher":"Elsevier BV","issue":"2-4","license":[{"start":{"date-parts":[[1999,11,1]],"date-time":"1999-11-01T00:00:00Z","timestamp":941414400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Speech Communication"],"published-print":{"date-parts":[[1999,11]]},"DOI":"10.1016\/s0167-6393(99)00036-9","type":"journal-article","created":{"date-parts":[[2003,4,5]],"date-time":"2003-04-05T03:57:58Z","timestamp":1049515078000},"page":"177-191","source":"Crossref","is-referenced-by-count":24,"title":["Maximum likelihood modelling of pronunciation variation"],"prefix":"10.1016","volume":"29","author":[{"given":"Trym","family":"Holter","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Torbj\u00f8rn","family":"Svendsen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0167-6393(99)00036-9_BIB1","doi-asserted-by":"crossref","unstructured":"Asadi, A., Schwartz, R., Makhoul, J., 1991. Automatic modeling for adding new words to a large vocabulary speech recognition system. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, Toronto, Canada, pp. 305\u2013308","DOI":"10.1109\/ICASSP.1991.150337"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB2","unstructured":"Bacchiani, M., Ostendorf, M., 1998. Joint acoustic design and lexicon generation. In: Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition. ESCA, Rolduc, The Netherlands. pp. 7\u201312"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB3","doi-asserted-by":"crossref","unstructured":"Bahl, L.R., Das, S., deSouza, P.V., Epstein, M., Mercer, R.L., Merialdo, B., Nahamoo, D., Picheny, M.A., Powell, J., 1991. Automatic phonetic baseform determination. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, Toronto, Canada, pp. 173\u2013176","DOI":"10.1109\/ICASSP.1991.150305"},{"issue":"4","key":"10.1016\/S0167-6393(99)00036-9_BIB4","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1109\/89.242490","article-title":"A method for the construction od acoustic markov models for words","volume":"1","author":"Bahl","year":"1993","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/S0167-6393(99)00036-9_BIB5","unstructured":"Cohen, M., 1989. Phonological structures for speech recognition. Ph.D. Thesis, University of California, Berkeley"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB6","doi-asserted-by":"crossref","unstructured":"Gillick, L., Cox, S.J., 1989. Some statistical issues in the comparison of speech recognition algorithms. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, Glasgow, Scotland, pp. 532\u2013535","DOI":"10.1109\/ICASSP.1989.266481"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB7","doi-asserted-by":"crossref","unstructured":"Haeb-Umbach, R., Beyerlein, P., Thelen, E., 1995. Automatic transcription of unknown words in a speech recognition system. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, Detroit, USA, pp. 840\u2013843","DOI":"10.1109\/ICASSP.1995.479825"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB8","unstructured":"Holter, T., 1997. Maximum likelihood modelling of pronunciation in automatic speech recognition. Ph.D. Thesis, Norwegian University of Science and Technology"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB9","doi-asserted-by":"crossref","unstructured":"Holter, T. and Svendsen, T., 1996. A comparison of lexicon-building methods for subword-based speech recognisers. In: Proceedings of the IEEE Region 10 Conference on Digital Signal Processing (TENCON). IEEE, Perth, Australia, pp. 102\u2013106","DOI":"10.1109\/TENCON.1996.608722"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB10","doi-asserted-by":"crossref","unstructured":"Holter, T., Svendsen, T., 1997a. Combined optimisation of baseforms and model parameters in speech recognition based on acoustic sub-word units. In: Proceedings of the 1997 IEEE Workshop on Speech Recognition and Understanding. IEEE, Santa Barbara, USA, pp. 199\u2013206","DOI":"10.1109\/ASRU.1997.659006"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB11","doi-asserted-by":"crossref","unstructured":"Holter, T., Svendsen, T., 1997b. Incorporating linguistic knowledge and automatic baseform generation in acoustic subword based speech recognition. In: Proceedings of the European Conference on Speech Communication and Technology (EUROSPEECH). Rhodes, Greece pp. 1159\u20131162","DOI":"10.21437\/Eurospeech.1997-13"},{"issue":"3","key":"10.1016\/S0167-6393(99)00036-9_BIB12","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1121\/1.395275","article-title":"Review of text-to-speech conversion for English","volume":"82","author":"Klatt","year":"1987","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(99)00036-9_BIB13","unstructured":"Lee, C.-H., Soong, F.K., Juang, B.-H., 1988. A segment model approach to speech recognition. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, New York, pp. 501\u2013504"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB14","doi-asserted-by":"crossref","unstructured":"Lee, C.-H., Juang, B.-H., Soong, F.K., Rabiner, L.R., 1989. Word recognition using whole word and subword models. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, Glasgow, Scotland, pp. 683\u2013686","DOI":"10.1109\/ICASSP.1989.266519"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB15","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1109\/TCOM.1980.1094577","article-title":"An algorithm for vector quantizer design","volume":"28","author":"Linde","year":"1980","journal-title":"IEEE Trans. Commun."},{"issue":"5","key":"10.1016\/S0167-6393(99)00036-9_BIB16","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1109\/TSMC.1978.4309979","article-title":"A sentence-to-sentence clustering procedure for pattern analysis","volume":"8","author":"Lu","year":"1978","journal-title":"IEEE Trans. Syst. Man Cybernet. SMC"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB17","doi-asserted-by":"crossref","unstructured":"Lucassen, J.M., Mercer, R.L., 1984. An information theoretic approach to the automatic determination of phonemic baseforms. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, San Diego, USA, pp. 42.5.1\u201342.5.4","DOI":"10.1109\/ICASSP.1984.1172810"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB18","unstructured":"Mokbel, H., Jouvet, D., 1998. Derivation of the optimal phonetic transcription set for a word from its acoustic realisations. In: Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition. ESCA, Rolduc, The Netherlands, pp. 73\u201378"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB19","series-title":"Problem-Solving Methods in Artificial Intelligence","author":"Nilsson","year":"1971"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB20","unstructured":"NIST Speech Disc 2-4.2, 1992. Resource Management continuous speech database (RM1) \u2013 Development test and evaluation test data and scoring software"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB21","doi-asserted-by":"crossref","unstructured":"Paliwal, K.K., 1990. Lexicon-building methods for an acoustic sub-word based speech recognizer. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, Albuquerque, USA, pp. 729\u2013732","DOI":"10.1109\/ICASSP.1990.115888"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB22","doi-asserted-by":"crossref","unstructured":"Price, P., Fisher, W.M., Bernstein, J., Pallet, D.S., 1988. The DARPA 1000-word Resource Management database for continuous speech recognition. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, New York, pp. 651\u2013654","DOI":"10.1109\/ICASSP.1988.196669"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB23","doi-asserted-by":"crossref","unstructured":"Ramabhadran, B., Bahl, L.R., deSouza, P.V., Padmanabhan, M., 1998. Acoustics-only based automatic phonetic baseform generation. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, Seattle, USA, pp. 309\u2013312","DOI":"10.1109\/ICASSP.1998.674429"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB24","doi-asserted-by":"crossref","unstructured":"Sloboda, T., 1995. Dictionary learning: Performance through consistency. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, Detroit, USA, pp. 453\u2013456","DOI":"10.1109\/ICASSP.1995.479626"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB25","doi-asserted-by":"crossref","unstructured":"Sloboda, T., Waibel, A., 1996. Dictionary learning for spontaneous speech recognition. In: Proceedings of the International Conference on Spoken Language Processing (ICSLP). Philadelphia, USA. pp. 2328\u20132331","DOI":"10.1109\/ICSLP.1996.607274"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB26","doi-asserted-by":"crossref","unstructured":"Soong, F.K., Huang, E.-F., 1991. A tree-trellis based fast search for finding the N best sentence hypotheses in continuous speech recognition. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, Toronto, Canada, pp. 705\u2013708","DOI":"10.1109\/ICASSP.1991.150437"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB27","unstructured":"Strik, H., Cucchiarini, C., 1998. Modeling pronunciation variation for ASR: Overview and comparison of methods. In: Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition. ESCA, Rolduc, The Netherlands, pp. 137\u2013144"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB28","doi-asserted-by":"crossref","unstructured":"Svendsen, T., Paliwal, K.K., Harborg, E., Hus\u00f8y, P.O., 1989. An improved sub-word based speech recognizer. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, Glasgow, Scotland, pp. 108\u2013111","DOI":"10.1109\/ICASSP.1989.266375"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB29","doi-asserted-by":"crossref","unstructured":"Svendsen, T., Soong, F.K., Purnhagen, H., 1995. Optimizing baseforms for HMM-based speech recognition. In: Proceedings of the European Conference on Speech Communication and Technology (EUROSPEECH). Madrid, Spain, pp. 783\u2013786","DOI":"10.21437\/Eurospeech.1995-179"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB30","doi-asserted-by":"crossref","unstructured":"Wilpon, J.G., Juang, B.-H., Rabiner, L.R., 1987. An investigation on the use of acoustic sub-word units for automatic speech recognition. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, Dallas, USA, pp. 821\u2013824","DOI":"10.1109\/ICASSP.1987.1169589"},{"key":"10.1016\/S0167-6393(99)00036-9_BIB31","unstructured":"Young, S.J., Jansen, J., Odell, J., Ollason, D., Woodland, P., 1993. HTK: Hidden Markov Model Toolkit V1.5. Cambridge University Engineering Department Speech Group and Entropic Research Laboratories"},{"issue":"3","key":"10.1016\/S0167-6393(99)00036-9_BIB32","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1109\/89.232618","article-title":"A speaker-independent continuous speech recognition system using continuous mixture Gaussian density HMM of phoneme-sized units","volume":"1","author":"Zhao","year":"1993","journal-title":"IEEE Trans. Speech Audio Process."}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639399000369?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639399000369?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2023,4,15]],"date-time":"2023-04-15T21:56:36Z","timestamp":1681595796000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639399000369"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1999,11]]},"references-count":32,"journal-issue":{"issue":"2-4","published-print":{"date-parts":[[1999,11]]}},"alternative-id":["S0167639399000369"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6393(99)00036-9","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[1999,11]]}}}