{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T10:57:02Z","timestamp":1769684222523,"version":"3.49.0"},"reference-count":43,"publisher":"Elsevier BV","issue":"4","license":[{"start":{"date-parts":[[2006,10,1]],"date-time":"2006-10-01T00:00:00Z","timestamp":1159660800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computer Speech &amp; Language"],"published-print":{"date-parts":[[2006,10]]},"DOI":"10.1016\/j.csl.2005.07.002","type":"journal-article","created":{"date-parts":[[2005,8,30]],"date-time":"2005-08-30T11:21:25Z","timestamp":1125400885000},"page":"515-541","source":"Crossref","is-referenced-by-count":68,"title":["Unlimited vocabulary speech recognition with morph language models applied to Finnish"],"prefix":"10.1016","volume":"20","author":[{"given":"Teemu","family":"Hirsim\u00e4ki","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathias","family":"Creutz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vesa","family":"Siivola","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mikko","family":"Kurimo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sami","family":"Virpioja","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Janne","family":"Pylkk\u00f6nen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.csl.2005.07.002_bib1","doi-asserted-by":"crossref","unstructured":"Argamon, S., Akiva, N., Amir, A., Kapah., O., 2004. Efficient unsupervised recursive word segmentation using minimum description length. In: Proceedings of The 20th International Conference on Computational Linguistics (COLING).","DOI":"10.3115\/1220355.1220507"},{"issue":"1","key":"10.1016\/j.csl.2005.07.002_bib2","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1006\/csla.2001.0185","article-title":"An overview of decoding techniques for large vocabulary continuous speech recognition","volume":"16","author":"Aubert","year":"2002","journal-title":"Computer Speech and Language"},{"key":"10.1016\/j.csl.2005.07.002_bib3","doi-asserted-by":"crossref","unstructured":"Bilmes, J.A., Kirchhoff, K., 2003. Factored language models and generalized parallel backoff. In: Proceedings of the Human Language Technology Conference (HLT\/NAACL), pp. 4\u20136.","DOI":"10.3115\/1073483.1073485"},{"key":"10.1016\/j.csl.2005.07.002_bib4","doi-asserted-by":"crossref","unstructured":"Bonafonte, A., Ros, X., Mari\u00f1o, J.B., 1993. An efficient algorithm to find the best state sequence in HSMM. In: Proceedings of the 3rd European Conference on Speech Communication and Technology (Eurospeech), pp. 1547\u20131550.","DOI":"10.21437\/Eurospeech.1993-346"},{"key":"10.1016\/j.csl.2005.07.002_bib5","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1023\/A:1007541817488","article-title":"An efficient, probabilistically sound algorithm for segmentation and word discovery","volume":"34","author":"Brent","year":"1999","journal-title":"Machine Learning"},{"key":"10.1016\/j.csl.2005.07.002_bib6","unstructured":"Byrne, W., Haji\u010d, J., Ircing, P., Jelinek, F., Khudanpur, S., Krbec, P., Psutka, J., 2001. On large vocabulary continuous speech recognition of highly inflectional language \u2013 Czech. In: Proceedings of the 7th European Conference on Speech Communication and Technology (Eurospeech), pp. 487\u2013489."},{"key":"10.1016\/j.csl.2005.07.002_bib7","doi-asserted-by":"crossref","unstructured":"Byrne, W.J., Haji\u010d, J., Krbec, P., Ircing, P., Psutka, J., 2000. Morpheme based language models for speech recognition of Czech. In: Proceedings of the Third, International Workshop on Text, Speech, Dialogue (TSD), pp. 211\u2013216.","DOI":"10.1007\/3-540-45323-7_36"},{"key":"10.1016\/j.csl.2005.07.002_bib8","unstructured":"Chen, S.F., 1996. Building probabilistic models for natural language. Ph.D. Thesis, Harvard University."},{"issue":"4","key":"10.1016\/j.csl.2005.07.002_bib9","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1006\/csla.1999.0128","article-title":"An empirical study of smoothing techniques for language modeling","volume":"13","author":"Chen","year":"1999","journal-title":"Computer Speech and Language"},{"key":"10.1016\/j.csl.2005.07.002_bib10","doi-asserted-by":"crossref","unstructured":"Creutz, M., 2003. Unsupervised segmentation of words using prior distributions of morph length and frequency. In: Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics (ACL), pp. 280\u2013287.","DOI":"10.3115\/1075096.1075132"},{"key":"10.1016\/j.csl.2005.07.002_bib11","doi-asserted-by":"crossref","unstructured":"Creutz, M., Lagus, K., 2002. Unsupervised discovery of morphemes. In: Proceedings of the Workshop on Morphological and Phonological Learning of ACL-02, pp. 21\u201330.","DOI":"10.3115\/1118647.1118650"},{"key":"10.1016\/j.csl.2005.07.002_bib12","unstructured":"Creutz, M., Lagus, K., 2005. Unsupervised morpheme segmentation and morphology induction from text corpora using Morfessor 1.0. Tech. Rep. A81, Publications in Computer and Information Science, Helsinki University of Technology. Available from: <https:\/\/2.zoppoz.workers.dev:443\/http\/www.cis.hut.fi\/projects\/morpho\/>."},{"key":"10.1016\/j.csl.2005.07.002_bib13","unstructured":"Creutz, M., Lind\u00e9n, K., 2004. Morpheme segmentation gold standards for Finnish and English. Tech. Rep. A77, Publications in Computer and Information Science, Helsinki University of Technology. Available from: <https:\/\/2.zoppoz.workers.dev:443\/http\/www.cis.hut.fi\/projects\/morpho\/>."},{"issue":"3","key":"10.1016\/j.csl.2005.07.002_bib14","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1016\/S0167-6393(97)00048-4","article-title":"Inference of variable-length linguistic and acoustic units by multigrams","volume":"23","author":"Deligne","year":"1997","journal-title":"Speech Communication"},{"issue":"3","key":"10.1016\/j.csl.2005.07.002_bib15","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1109\/89.759034","article-title":"Semi-tied covariance matrices for hidden Markov models","volume":"7","author":"Gales","year":"1999","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"10.1016\/j.csl.2005.07.002_bib16","doi-asserted-by":"crossref","unstructured":"Geutner, P., Finke, M., Scheytt, P., 1998. Adaptive vocabularies for transcribing multilingual broadcast news. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). vol. 2, pp. 925\u2013928.","DOI":"10.1109\/ICASSP.1998.675417"},{"issue":"2","key":"10.1016\/j.csl.2005.07.002_bib17","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1162\/089120101750300490","article-title":"Unsupervised learning of the morphology of a natural language","volume":"27","author":"Goldsmith","year":"2001","journal-title":"Computational Linguistics"},{"key":"10.1016\/j.csl.2005.07.002_bib18","doi-asserted-by":"crossref","unstructured":"Goodman, J.T., 2001. A bit of progress in language modeling, extended version. Tech. Rep. MSR-TR-2001-72, Microsoft Research, Extended version of a paper with the same title published in Computer Speech and Language 15, 403\u2013434.","DOI":"10.1006\/csla.2001.0174"},{"key":"10.1016\/j.csl.2005.07.002_bib19","doi-asserted-by":"crossref","unstructured":"Hacioglu, K., Pellom, B., Ciloglu, T., Ozturk, O., Kurimo, M., Creutz, M., 2003. On lexicon creation for Turkish LVCSR. In: Proceedings of the 8th European Conference on Speech Communication and Technology (Eurospeech), pp. 1165\u20131168.","DOI":"10.21437\/Eurospeech.2003-378"},{"key":"10.1016\/j.csl.2005.07.002_bib20","unstructured":"Hakulinen, L., 1979. Suomen kielen rakenne ja kehitys (The structure and development of the Finnish language), 4th Ed., Kustannus-Oy Otava."},{"key":"10.1016\/j.csl.2005.07.002_bib21","doi-asserted-by":"crossref","unstructured":"Johnson, S., Jourlin, P., Moore, G., Jones, K.S., Woodland, P., 1999. The Cambridge University spoken document retrieval system. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 49\u201352.","DOI":"10.1109\/ICASSP.1999.758059"},{"key":"10.1016\/j.csl.2005.07.002_bib22","doi-asserted-by":"crossref","unstructured":"Juang, B.H., Rabiner, L.R., Levinson, S.E., Sondhi, M.M., 1985. Recent developments in the application of hidden Markov models to speaker-independent isolated word recognition. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 9\u201312.","DOI":"10.1109\/ICASSP.1985.1168453"},{"key":"10.1016\/j.csl.2005.07.002_bib23","doi-asserted-by":"crossref","unstructured":"Kirchhoff, K., Bilmes, J., Das, S., Duta, N., Egan, M., Ji, G., He, F., Henderson, J., Liu, D., Noamany, M., Schone, P., Schwartz, R., Vergyri, D., 2003. Novel approaches to Arabic speech recognition: Report from the 2002 Johns-Hopkins workshop. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 1, pp. 344\u2013347.","DOI":"10.1109\/ICASSP.2003.1198788"},{"key":"10.1016\/j.csl.2005.07.002_bib24","doi-asserted-by":"crossref","unstructured":"Kneissler, J., Klakow, D., 2001. Speech recognition for huge vocabularies by using optimized sub-word units. In: Proceedings of the 7th European Conference on Speech Communication and Technology (Eurospeech), pp. 69\u201372.","DOI":"10.21437\/Eurospeech.2001-16"},{"key":"10.1016\/j.csl.2005.07.002_bib25","doi-asserted-by":"crossref","unstructured":"Koskenniemi, K., 1983. Two-level morphology: a general computational model for word-form recognition and production. Ph.D. Thesis, University of Helsinki.","DOI":"10.3115\/980431.980529"},{"key":"10.1016\/j.csl.2005.07.002_bib26","unstructured":"Kurimo, M., 1997. Using self-organizing maps and learning vector quantization for mixture density hidden Markov models. Ph.D. Thesis, Helsinki University of Technology."},{"issue":"3\u20134","key":"10.1016\/j.csl.2005.07.002_bib27","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1016\/S0167-6393(02)00031-6","article-title":"Korean large vocabulary continuous speech recognition with morpheme-based recognition units","volume":"39","author":"Kwon","year":"2003","journal-title":"Speech Communication"},{"key":"10.1016\/j.csl.2005.07.002_bib28","doi-asserted-by":"crossref","unstructured":"McTait, K., Adda-Decker, M., 2003. The 300k LIMSI German broadcast news transcription system. In: Proceedings of the 8th European Conference on Speech Communication and Technology (Eurospeech), pp. 213\u2013216.","DOI":"10.21437\/Eurospeech.2003-102"},{"key":"10.1016\/j.csl.2005.07.002_bib29","series-title":"Introduction to Probability and Statistics","author":"Milton","year":"1995"},{"key":"10.1016\/j.csl.2005.07.002_bib30","doi-asserted-by":"crossref","unstructured":"Ordelman, R., van Hessen, A., de Jong, F., 2003. Compound decomposition in Dutch large vocabulary speech recognition. In: Proceedings of the 8th European Conference on Speech Communication and Technology (Eurospeech), pp. 225\u2013228.","DOI":"10.21437\/Eurospeech.2003-105"},{"key":"10.1016\/j.csl.2005.07.002_bib31","unstructured":"Pylkk\u00f6nen, J., Kurimo, M., 2004. Using phone durations in Finnish large vocabulary continuous speech recognition. In: Proceedings of the 6th Nordic Signal Processing Symposium (Norsig), pp. 324\u2013326."},{"issue":"2","key":"10.1016\/j.csl.2005.07.002_bib32","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","article-title":"A tutorial on hidden Markov models and selected applications in speech recognition","volume":"77","author":"Rabiner","year":"1989","journal-title":"Proceedings of the IEEE"},{"key":"10.1016\/j.csl.2005.07.002_bib33","first-page":"79","article-title":"Stochastic complexity in statistical inquiry","volume":"15","author":"Rissanen","year":"1989","journal-title":"World Scientific Series in Computer Science"},{"key":"10.1016\/j.csl.2005.07.002_bib34","doi-asserted-by":"crossref","unstructured":"Russell, M.J., Cook, A.E., 1987. Experimental evaluation of duration modelling techniques for automatic speech recognition. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 4, pp. 2376\u20132379.","DOI":"10.1109\/ICASSP.1987.1169918"},{"key":"10.1016\/j.csl.2005.07.002_bib35","doi-asserted-by":"crossref","unstructured":"Siivola, V., Hirsim\u00e4ki, T., Creutz, M., Kurimo, M., 2003. Unlimited vocabulary speech recognition based on morphs discovered in an unsupervised manner. In: Proceedings of the 8th European Conference on Speech Communication and Technology (Eurospeech), pp. 2293\u20132296.","DOI":"10.21437\/Eurospeech.2003-640"},{"key":"10.1016\/j.csl.2005.07.002_bib36","doi-asserted-by":"crossref","unstructured":"Stolcke, A., 2002. SRILM\u2013an extensible language modeling toolkit. In: Proceedings of the 7th International Conference on Spoken Language Processing (ICSLP), pp. 901-904. Available from: <https:\/\/2.zoppoz.workers.dev:443\/http\/www.speech.sri.com\/projects\/srilm\/>.","DOI":"10.21437\/ICSLP.2002-303"},{"key":"10.1016\/j.csl.2005.07.002_bib37","doi-asserted-by":"crossref","unstructured":"Szarvas, M., Furui, S., 2003. Evaluation of the stochastic morphosyntactic language model on a one million word Hungarian task. In: Proceedings of the 8th European Conference on Speech Communication and Technology (Eurospeech), pp. 2297\u20132300.","DOI":"10.21437\/Eurospeech.2003-641"},{"issue":"3","key":"10.1016\/j.csl.2005.07.002_bib38","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1162\/089120100561746","article-title":"A compression based algorithm for Chinese word segmentation","volume":"26","author":"Teahan","year":"2000","journal-title":"Computational Linguistics"},{"issue":"3","key":"10.1016\/j.csl.2005.07.002_bib39","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1162\/089120101317066113","article-title":"A statistical model for word discovery in transcribed speech","volume":"27","author":"Venkataraman","year":"2001","journal-title":"Computational Linguistics"},{"key":"10.1016\/j.csl.2005.07.002_bib40","doi-asserted-by":"crossref","unstructured":"Vergyri, D., Kirchhoff, K., Duh, K., Stolcke, A., 2004. Morphology-based language modeling for Arabic speech recognition. In: Proceedings of the 8th International Conference on Spoken Language Processing (ICSLP), vol. 3, pp. 2245\u20132248.","DOI":"10.21437\/Interspeech.2004-495"},{"key":"10.1016\/j.csl.2005.07.002_bib41","doi-asserted-by":"crossref","unstructured":"Whittaker, E., Raj, B., 2001. Quantization-based language model compression. In: Proceedings of the 7th European Conference on Speech Communication and Technology (Eurospeech), vol. 1, pp. 33\u201336.","DOI":"10.21437\/Eurospeech.2001-8"},{"key":"10.1016\/j.csl.2005.07.002_bib42","doi-asserted-by":"crossref","unstructured":"Whittaker, E., Woodland, P., 2000. Particle-based language modelling. In: Proceedings of the 6th International Conference on Spoken Language Processing (ICSLP), pp. 170\u2013173.","DOI":"10.21437\/ICSLP.2000-42"},{"key":"10.1016\/j.csl.2005.07.002_bib43","doi-asserted-by":"crossref","unstructured":"Willett, D., Neukirchen, C., Rigoll, G., 2000. Ducoder - the Duisburg University LVCSR stackdecoder. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1555\u20131558.","DOI":"10.1109\/ICASSP.2000.861966"}],"container-title":["Computer Speech &amp; Language"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0885230805000331?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0885230805000331?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2023,5,4]],"date-time":"2023-05-04T09:33:30Z","timestamp":1683192810000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/linkinghub.elsevier.com\/retrieve\/pii\/S0885230805000331"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,10]]},"references-count":43,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2006,10]]}},"alternative-id":["S0885230805000331"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.csl.2005.07.002","relation":{},"ISSN":["0885-2308"],"issn-type":[{"value":"0885-2308","type":"print"}],"subject":[],"published":{"date-parts":[[2006,10]]}}}