{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T01:03:13Z","timestamp":1777510993644,"version":"3.51.4"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2016,2,10]],"date-time":"2016-02-10T00:00:00Z","timestamp":1455062400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100005789","name":"Tallinna Tehnika\u00fclikool (EE)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005789","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003510","name":"Haridus- ja Teadusministeerium (EE)","doi-asserted-by":"publisher","award":["0140007s12"],"award-info":[{"award-number":["0140007s12"]}],"id":[{"id":"10.13039\/501100003510","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002341","name":"Suomen Akatemia (FI)","doi-asserted-by":"publisher","award":["251170"],"award-info":[{"award-number":["251170"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003125","name":"Suomen Kulttuurirahasto (FI)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003125","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Lang Resources & Evaluation"],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1007\/s10579-016-9336-9","type":"journal-article","created":{"date-parts":[[2016,2,10]],"date-time":"2016-02-10T08:48:39Z","timestamp":1455094119000},"page":"961-987","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Modeling under-resourced languages for speech recognition"],"prefix":"10.1007","volume":"51","author":[{"given":"Mikko","family":"Kurimo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seppo","family":"Enarvi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ottokar","family":"Tilk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matti","family":"Varjokallio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andr\u00e9","family":"Mansikkaniemi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tanel","family":"Alum\u00e4e","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,2,10]]},"reference":[{"key":"9336_CR1","doi-asserted-by":"crossref","unstructured":"Adde, L., & Svendsen, T. (2011). Pronunciation variation modeling of non-native proper names by discriminative tree search. In Proceedings of the 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 4928\u20134931). Prague, Czech Republic.","DOI":"10.1109\/ICASSP.2011.5947461"},{"key":"9336_CR2","doi-asserted-by":"crossref","unstructured":"Alum\u00e4e, T. (2013). Multi-domain neural network language model. In Proceedings of the 14th Annual Conference of the International Speech Communication Association (INTERSPEECH 2013) (pp. 2182\u20132186).","DOI":"10.21437\/Interspeech.2013-515"},{"key":"9336_CR3","unstructured":"Alum\u00e4e, T. (2014). Recent improvements in Estonian LVCSR. In Spoken Language Technologies for Under-Resourced Languages. St. Petersburg, Russia."},{"key":"9336_CR4","first-page":"1137","volume":"3","author":"Y Bengio","year":"2003","unstructured":"Bengio, Y., Ducharme, R., Vincent, P., & Jauvin, C. (2003). A neural probabilistic language model. Journal of Machine Learning Research, 3, 1137\u20131155.","journal-title":"Journal of Machine Learning Research"},{"issue":"5","key":"9336_CR5","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1016\/j.specom.2008.01.002","volume":"50","author":"M Bisani","year":"2008","unstructured":"Bisani, M., & Ney, H. (2008). Joint-sequence models for grapheme-to-phoneme conversion. Speech Communication, 50(5), 434\u2013451. doi: 10.1016\/j.specom.2008.01.002 .","journal-title":"Speech Communication"},{"key":"9336_CR6","doi-asserted-by":"publisher","unstructured":"Creutz, M., & Lagus, K. (2002). Unsupervised discovery of morphemes. In Proceedings of the ACL 2002 workshop on morphological and phonological learning, MPL \u201902, Vol. 6 (pp. 21\u201330). Association for Computational Linguistics, Stroudsburg, PA, USA. doi: 10.3115\/1118647.1118650 .","DOI":"10.3115\/1118647.1118650"},{"issue":"3","key":"9336_CR7","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1016\/S0167-6393(97)00048-4","volume":"23","author":"S Deligne","year":"1997","unstructured":"Deligne, S., & Bimbot, F. (1997). Inference of variable-length linguistic and acoustic units by multigrams. Speech Communication, 23(3), 223\u2013241.","journal-title":"Speech Communication"},{"key":"9336_CR9","unstructured":"Enarvi, S., & Kurimo, M. (2013a). Studies on training text selection for conversational finnish language modeling. In Proceedings of the 10th International Workshop on Spoken Language Translation (IWSLT 2013) (pp. 256\u2013263). Heidelberg, Germany."},{"key":"9336_CR8","doi-asserted-by":"crossref","unstructured":"Enarvi, S., & Kurimo, M. (2013b). A novel discriminative method for pruning pronunciation dictionary entries. In Proceedings of the 7th International Conference on Speech Technology and Human\u2013Computer Dialogue (pp. 113\u2013116). Cluj-Napoca, Romania.","DOI":"10.1109\/SpeD.2013.6682659"},{"key":"9336_CR10","doi-asserted-by":"crossref","unstructured":"Gandhe, A., Metze, F., & Lane, I. (2014). Neural network language models for low resource languages. In Proceedings of the 15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014).","DOI":"10.21437\/Interspeech.2014-560"},{"key":"9336_CR11","doi-asserted-by":"crossref","unstructured":"Hirsim\u00e4ki, T., & Kurimo, M. (2009). Analysing recognition errors in unlimited-vocabulary speech recognition. In Proceedings of the North American Chapter of the Association for Computational Linguistics\u2014Human Language Technologies 2009 Conference (NAACL 2009) (pp. 193\u2013196). Boulder, Colorado, USA.","DOI":"10.3115\/1620853.1620906"},{"issue":"4","key":"9336_CR12","doi-asserted-by":"publisher","first-page":"724","DOI":"10.1109\/TASL.2008.2012323","volume":"17","author":"T Hirsim\u00e4ki","year":"2009","unstructured":"Hirsim\u00e4ki, T., Pylkk\u00f6nen, J., & Kurimo, M. (2009). Importance of high-order n-gram models in morph-based speech recognition. IEEE Transactions on Audio, Speech & Language Processing, 17(4), 724\u2013732. doi: 10.1109\/TASL.2008.2012323 .","journal-title":"IEEE Transactions on Audio, Speech & Language Processing"},{"key":"9336_CR13","unstructured":"Iskra, D. J., Grosskopf, B., Marasek, K., van den Heuvel, H., Diehl, F., & Kie\u00dfling, A. (2002). SPEECON\u2014speech databases for consumer devices: Database specification and validation. In Proceedings of the Third International Conference on Language Resources and Evaluation (LREC 2002). Canary Islands, Spain."},{"key":"9336_CR14","doi-asserted-by":"publisher","unstructured":"Klakow, D. (2000). Selecting articles from the language model training corpus. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2000), Vol. 3 (pp. 1695\u20131698). IEEE Computer Society. doi: 10.1109\/ICASSP.2000.862077 .","DOI":"10.1109\/ICASSP.2000.862077"},{"key":"9336_CR15","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1007\/978-3-642-40585-3_38","volume":"8082","author":"J Lehecka","year":"2013","unstructured":"Lehecka, J., & Svec, J. (2013). Improving speech recognition by detecting foreign inclusions and generating pronunciations. Text, Speech, and Dialogue, Lecture Notes in Computer Science, 8082, 295\u2013302.","journal-title":"Text, Speech, and Dialogue, Lecture Notes in Computer Science"},{"key":"9336_CR16","unstructured":"Leinonen, J. (2015). Automatic speech recognition for human\u2013robot interaction using an under-resourced language. Aalto University, School of Electrical Engineering, Department of Signal Processing and Acoustics, Espoo."},{"key":"9336_CR17","first-page":"145","volume-title":"Phonetics of Russian and Finnish. General introduction. Spontaneous and read-aloud speech","author":"M Lennes","year":"2009","unstructured":"Lennes, M. (2009). Segmental features in spontaneous and read-aloud Finnish. In V. de Silva & R. Ullakonoja (Eds.), Phonetics of Russian and Finnish. General introduction. Spontaneous and read-aloud speech (pp. 145\u2013166). Bern: Peter Lang GmbH."},{"key":"9336_CR18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3384\/nejlt.2000-1533.09111","volume":"1","author":"K Linden","year":"2009","unstructured":"Linden, K. (2009). Entry generation for new words by analogy for morphological lexicons. Northern European Journal of Language Technology, 1, 1\u201325.","journal-title":"Northern European Journal of Language Technology"},{"key":"9336_CR19","doi-asserted-by":"crossref","unstructured":"Maison, B., Chen, S., & Cohen, P. S. (2003). Pronunciation modeling for names of foreign origin. In Proceedings of the 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) (pp. 429\u2013434).","DOI":"10.1109\/ASRU.2003.1318479"},{"key":"9336_CR20","doi-asserted-by":"crossref","unstructured":"Mansikkaniemi, A., & Kurimo, M. (2013). Unsupervised topic adaptation for morph-based speech recognition. In Proceedings of the 14th Annual Conference of the International Speech Communication Association (INTERSPEECH 2013) (pp. 2693\u20132697). Lyon, France.","DOI":"10.21437\/Interspeech.2013-619"},{"key":"9336_CR21","unstructured":"Moore, R. C., & Lewis, W. (2010). Intelligent selection of language model training data. In Proceedings of the ACL 2010 Conference Short Papers, ACLShort \u201910 (pp. 220\u2013224). Association for Computational Linguistics, Stroudsburg, PA, USA. http:\/\/dl.acm.org\/citation.cfm?id=1858842.1858883 ."},{"issue":"8","key":"9336_CR22","doi-asserted-by":"crossref","first-page":"1224","DOI":"10.1109\/5.880081","volume":"88","author":"H Ney","year":"2000","unstructured":"Ney, H., & Ortmanns, S. (2000). Progress in dynamic programming search for LVCSR. Proceedings of the IEEE, 88(8), 1224\u20131240.","journal-title":"Proceedings of the IEEE"},{"key":"9336_CR23","doi-asserted-by":"crossref","unstructured":"Park, J., Liu, X., Gales, M. J. F., & Woodland, P. C. (2010). Improved neural network based language modelling and adaptation. In Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010) (pp. 1041\u20131044).","DOI":"10.21437\/Interspeech.2010-342"},{"key":"9336_CR24","unstructured":"Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motlicek, P., Qian, Y., Schwarz, P., Silovsky, J., Stemmer, G., & Vesely, K. (2011). The Kaldi speech recognition toolkit. In Proceedings of the 2011 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU). Hilton Waikoloa Village, Big Island, Hawaii: IEEE Signal Processing Society."},{"key":"9336_CR25","doi-asserted-by":"crossref","unstructured":"Povey, D., Kanevsky, D., Kingsbury, B., Ramabhadran, B., Saon, G., & Visweswariah, K. (2008). Boosted MMI for model and feature-space discriminative training. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2008) (pp. 4057\u20134060). IEEE.","DOI":"10.1109\/ICASSP.2008.4518545"},{"key":"9336_CR26","unstructured":"Pylkk\u00f6nen, J. (2005). An efficient one-pass decoder for Finnish large vocabulary continuous speech recognition. In Proceedings of the 2nd Baltic Conference on Human Language Technologies."},{"key":"9336_CR27","doi-asserted-by":"crossref","unstructured":"Saon, G., Soltau, H., Nahamoo, D., & Picheny, M. (2013). Speaker adaptation of neural network acoustic models using i-vectors. In Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) (pp. 55\u201359). IEEE.","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"9336_CR28","doi-asserted-by":"crossref","unstructured":"Schwenk, H., & Gauvain, J. L. (2004). Neural network language models for conversational speech recognition. In Proceedings of the 8th International Conference on Spoken Language Processing (INTERSPEECH 2004).","DOI":"10.21437\/Interspeech.2004-497"},{"key":"9336_CR29","doi-asserted-by":"crossref","unstructured":"Schwenk, H., & Gauvain, J. L. (2005). Training neural network language models on very large corpora. In Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing (pp. 201\u2013208). Association for Computational Linguistics.","DOI":"10.3115\/1220575.1220601"},{"key":"9336_CR30","doi-asserted-by":"crossref","unstructured":"Seide, F., Li, G., Chen, X., & Yu, D. (2011). Feature engineering in context-dependent deep neural networks for conversational speech transcription. In Proceedings of the 2011 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) (pp. 24\u201329). IEEE.","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"9336_CR31","unstructured":"Sethy, A., Georgiou, P. G., & Narayanan, S. (2006). Text data acquisition for domain-specific language models. In Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing, EMNLP \u201906 (pp. 382\u2013389). Association for Computational Linguistics, Stroudsburg, PA, USA. http:\/\/dl.acm.org\/citation.cfm?id=1610075.1610129 ."},{"issue":"1","key":"9336_CR32","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1109\/TASL.2008.2006654","volume":"17","author":"A Sethy","year":"2009","unstructured":"Sethy, A., Georgiou, P. G., Ramabhadran, B., & Narayanan, S. S. (2009). An iterative relative entropy minimization-based data selection approach for n-gram model adaptation. IEEE Transactions on Audio, Speech, and Language Processing, 17(1), 13\u201323.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9336_CR33","doi-asserted-by":"publisher","unstructured":"Shi, Y., Larson, M., & Jonker, C. M. (2014). Recurrent neural network language model adaptation with curriculum learning. Computer Speech & Language. doi: 10.1016\/j.csl.2014.11.004 .","DOI":"10.1016\/j.csl.2014.11.004"},{"issue":"5","key":"9336_CR34","doi-asserted-by":"crossref","first-page":"1617","DOI":"10.1109\/TASL.2007.896666","volume":"15","author":"V Siivola","year":"2007","unstructured":"Siivola, V., Hirsim\u00e4ki, T., & Virpioja, S. (2007). On growing and pruning Kneser\u2013Ney smoothed N-gram models. IEEE Transactions on Speech, Audio and Language Processing, 15(5), 1617\u20131624.","journal-title":"IEEE Transactions on Speech, Audio and Language Processing"},{"issue":"2","key":"9336_CR35","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1006\/csla.2002.0192","volume":"16","author":"A Sixtus","year":"2002","unstructured":"Sixtus, A., & Ney, H. (2002). From within-word model search to across-word model search in large vocabulary continuous speech recognition. Computer Speech and Language, 16(2), 245\u2013271.","journal-title":"Computer Speech and Language"},{"key":"9336_CR36","doi-asserted-by":"crossref","unstructured":"Soltau, H., & Saon, G. (2009). Dynamic network decoding revisited. In Proceedings of the 2009 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) (pp. 276\u2013281).","DOI":"10.1109\/ASRU.2009.5372904"},{"key":"9336_CR37","unstructured":"Tilk, O., & Alum\u00e4e, T. (2014). Multi-domain recurrent neural network language model for medical speech recognition. In Human language technologies\u2014The Baltic perspective, Vol. 268 (pp. 149\u2013152). Amsterdam: IOS Press."},{"key":"9336_CR39","doi-asserted-by":"crossref","unstructured":"Varjokallio, M., & Kurimo, M. (2014a). A word-level token-passing decoder for subword n-gram LVCSR. In Proceedings of the 2014 IEEE Spoken Language Technology Workshop (SLT) (pp. 495\u2013500). South Lake Tahoe, California and Nevada.","DOI":"10.1109\/SLT.2014.7078624"},{"key":"9336_CR38","unstructured":"Varjokallio, M., & Kurimo, M. (2014b). A toolkit for efficient learning of lexical units for speech recognition. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC 2014). Reykjavik, Iceland."},{"key":"9336_CR40","doi-asserted-by":"crossref","unstructured":"Varjokallio, M., Kurimo, M., & Virpioja, S. (2013). Learning a subword vocabulary based on unigram likelihood. In Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU). Olomouc, Czech Republic.","DOI":"10.1109\/ASRU.2013.6707697"},{"key":"9336_CR41","unstructured":"Young, S. J., Russell, N. H., & Thornton, J. H. S. (1989). Token passing: A simple conceptual model for connected speech recognition system. Tech. rep., Cambridge University Engineering Department."}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10579-016-9336-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-016-9336-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-016-9336-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-016-9336-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,3]],"date-time":"2022-06-03T21:00:42Z","timestamp":1654290042000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10579-016-9336-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,2,10]]},"references-count":41,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2017,12]]}},"alternative-id":["9336"],"URL":"https:\/\/doi.org\/10.1007\/s10579-016-9336-9","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"value":"1574-020X","type":"print"},{"value":"1574-0218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,2,10]]}}}