{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T07:06:28Z","timestamp":1725865588134},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319459240"},{"type":"electronic","value":"9783319459257"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-45925-7_11","type":"book-chapter","created":{"date-parts":[[2016,9,20]],"date-time":"2016-09-20T14:11:34Z","timestamp":1474380694000},"page":"133-144","source":"Crossref","is-referenced-by-count":2,"title":["Class n-Gram Models for Very Large Vocabulary Speech Recognition of Finnish and Estonian"],"prefix":"10.1007","author":[{"given":"Matti","family":"Varjokallio","sequence":"first","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"}]}],"member":"297","published-online":{"date-parts":[[2016,9,21]]},"reference":[{"key":"11_CR1","unstructured":"Aalto University: AaltoASR (2014). http:\/\/github.com\/aalto-speech\/AaltoASR\/"},{"issue":"1","key":"11_CR2","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1006\/csla.2001.0185","volume":"16","author":"XL Aubert","year":"2002","unstructured":"Aubert, X.L.: An overview of decoding techniques for large vocabulary continuous speech recognition. Comput. Speech Lang. 16(1), 89\u2013114 (2002)","journal-title":"Comput. Speech Lang."},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Botros, R., Irie, K., Sundermeyer, M., Ney, H.: On efficient training of word classes and their application to recurrent neural network language models. In: Proceedings of the INTERSPEECH, pp. 1443\u20131447, Dresden, Germany (2015)","DOI":"10.21437\/Interspeech.2015-345"},{"issue":"4","key":"11_CR4","first-page":"467","volume":"18","author":"PF Brown","year":"1992","unstructured":"Brown, P.F., deSouza, P.V., Mercer, R.L., Pietra, V.J.D., Lai, J.C.: Class-based n-gram models of natural language. Comput. Linguist. 18(4), 467\u2013470 (1992)","journal-title":"Comput. Linguist."},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Brychc\u00edn, T., Konopik, M.: Morphological based language models for inflectional languages. In: The 6th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, Prague, Czech Republic (2011)","DOI":"10.1109\/IDAACS.2011.6072829"},{"key":"11_CR6","unstructured":"Chen, S.F., Goodman, J.T.: An empirical study of smoothing techniques for language modeling. Technical report, TR-10-98. Computer Science Group, Harvard University (1998)"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Creutz, M., Lagus, K.: Unsupervised discovery of morphemes. In: Proceedings of the ACL 2002 Workshop on Morphological and Phonological Learning. MPL 2002, vol. 6, pp. 21\u201330 (2002)","DOI":"10.3115\/1118647.1118650"},{"issue":"1","key":"11_CR8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1322391.1322394","volume":"5","author":"M Creutz","year":"2007","unstructured":"Creutz, M., Stolcke, A., Hirsim\u00e4ki, T., Kurimo, M., Puurula, A., Pylkk\u00f6nen, J., Siivola, V., Varjokallio, M., Arisoy, E., Sara\u00e7lar, M.: Morph-based speech recognition and modeling of out-of-vocabulary words across languages. ACM Trans. Speech Lang. Process. 5(1), 1\u201329 (2007)","journal-title":"ACM Trans. Speech Lang. Process."},{"issue":"3","key":"11_CR9","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.: Inference of variable-length linguistic and acoustic units by multigrams. Speech Commun. 23(3), 223\u2013241 (1997)","journal-title":"Speech Commun."},{"issue":"4","key":"11_CR10","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1016\/j.csl.2005.07.002","volume":"20","author":"T Hirsim\u00e4ki","year":"2006","unstructured":"Hirsim\u00e4ki, T., Creutz, M., Siivola, V., Kurimo, M., Virpioja, S., Pylkk\u00f6nen, J.: Unlimited vocabulary speech recognition with morph language models applied to Finnish. Comput. Speech Lang. 20(4), 515\u2013541 (2006)","journal-title":"Comput. Speech Lang."},{"key":"11_CR11","unstructured":"Hirsim\u00e4ki, T., Kurimo, M.: Decoder issues in unlimited Finnish speech recognition. In: Proceedings of the 6th Nordic Signal Processing Symposium (Norsig 2004), pp. 320\u2013323, Espoo, Finland (2004)"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Hirsim\u00e4ki, T., Kurimo, M.: Analysing recognition errors in unlimited-vocabulary speech recognition. In: Proceedings of the HLT-NAACL, pp. 193\u2013196 (2009)","DOI":"10.3115\/1620853.1620906"},{"issue":"4","key":"11_CR13","doi-asserted-by":"crossref","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.: Importance of high-order n-gram models in morph-based speech recognition. IEEE Trans. Audio Speech Lang. Process. 17(4), 724\u2013732 (2009)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"11_CR14","unstructured":"Iskra, D.J., Grosskopf, B., Marasek, K., van den Heuvel, H., Diehl, F., Kie\u00dfling, A.: SPEECON - speech databases for consumer devices: database specification and validation. In: Proceedings of Third International Conference on Language Resources and Evaluation (LREC 2002), Canary Islands, Spain, May 2002"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Kneser, R., Ney, H.: Forming word classes by statistical clustering for statistical language modelling. In: Proceedings of the First International Conference on Quantitative Linguistics (QUALICO), pp. 221\u2013226, Trier, Germany (1991)","DOI":"10.1007\/978-94-011-1769-2_15"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Kneser, R., Ney, H.: Improved backing-off for m-gram language modeling. In: Proceedings of the 1995 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 181\u2013184 (1995)","DOI":"10.1109\/ICASSP.1995.479394"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Kurimo, M., Enarvi, S., Tilk, O., Varjokallio, M., Mansikkaniemi, A., Alum\u00e4e, T.: Modeling under-resourced languages for speech recognition. Lang. Res. Eval. 1\u201327 (2015)","DOI":"10.1007\/s10579-016-9336-9"},{"key":"11_CR18","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/S0167-6393(97)00062-9","volume":"24","author":"S Martin","year":"1998","unstructured":"Martin, S., Liermann, J., Ney, H.: Algorithms for bigram and trigram word clustering. Speech Commun. 24, 19\u201337 (1998)","journal-title":"Speech Commun."},{"key":"11_CR19","unstructured":"Meister, E., Meister, L., Metsvahi, R.: New speech corpora at IoC. In: XXVII Fonetiikan, 2012 \u2013 Phonetics Symposium 2012, pp. 30\u201333 (2012)"},{"key":"11_CR20","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1007\/978-3-540-49127-9_28","volume-title":"Handbook on Speech Processing and Speech Communication","author":"M Mohri","year":"2008","unstructured":"Mohri, M., Pereira, F.C.N., Riley, M.: Speech recognition with weighted finite state transducers. In: Benesty, J., Sondhi, M., Huang, Y. (eds.) Handbook on Speech Processing and Speech Communication, pp. 559\u2013584. Springer, Heidelberg (2008)"},{"issue":"8","key":"11_CR21","doi-asserted-by":"crossref","first-page":"1224","DOI":"10.1109\/5.880081","volume":"88","author":"H Ney","year":"2000","unstructured":"Ney, H., Ortmanns, S.: Progress in dynamic programming search for LVCSR. Proc. IEEE 88(8), 1224\u20131240 (2000)","journal-title":"Proc. IEEE"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Niesler, T., Whittaker, E., Woodland, P.: Comparison of part-of-speech and automatically derived category-based language models for speech recognition. In: Proceedings of the ICASSP, Seattle, USA (1998)","DOI":"10.1109\/ICASSP.1998.674396"},{"key":"11_CR23","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1006\/csla.1998.0115","volume":"13","author":"T Niesler","year":"1999","unstructured":"Niesler, T., Woodland, P.: Variable-length category n-gram language models. Comput. Speech Lang. 13, 99\u2013124 (1999)","journal-title":"Comput. Speech Lang."},{"issue":"1","key":"11_CR24","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1006\/csla.1999.0131","volume":"14","author":"S Ortmanns","year":"2000","unstructured":"Ortmanns, S., Ney, H.: Look-ahead techniques for fast beam search. Comput. Speech Lang. 14(1), 15\u201332 (2000)","journal-title":"Comput. Speech Lang."},{"key":"11_CR25","unstructured":"Pirinen, T.A.: Omorfi - free and open source morphological lexical database for Finnish. In: Proceedings of the 20th Nordic Conference of Computational Linguistics NODALIDA, Vilnius, Lithuania (2015)"},{"key":"11_CR26","unstructured":"Pylkk\u00f6nen, J.: An efficient one-pass decoder for Finnish large vocabulary continuous speech recognition. In: Proceedings of the 2nd Baltic Confrence on Human Language Technologies (2005)"},{"issue":"5","key":"11_CR27","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.: On growing and pruning Kneser-Ney smoothed n-gram models. IEEE Trans. Speech, Audio Lang. Process. 15(5), 1617\u20131624 (2007)","journal-title":"IEEE Trans. Speech, Audio Lang. Process."},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Silfverberg, M., Ruokolainen, T., Lind\u00e9n, K., Kurimo, M.: FinnPos: an open-source morphological tagging and lemmatization toolkit for Finnish. Lang. Resour. Eval. 1\u201316 (2015)","DOI":"10.1007\/s10579-015-9326-3"},{"issue":"2","key":"11_CR29","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.: From within-word model search to across-word model search in large vocabulary continuous speech recognition. Comput. Speech Lang. 16(2), 245\u2013271 (2002)","journal-title":"Comput. Speech Lang."},{"key":"11_CR30","doi-asserted-by":"crossref","unstructured":"Soltau, H., Saon, G.: Dynamic network decoding revisited. In: IEEE Automatic Speech Recognition and Understanding Workshop, pp. 276\u2013281 (2009)","DOI":"10.1109\/ASRU.2009.5372904"},{"key":"11_CR31","unstructured":"Tarjan, B., Fegy\u00f3, T., Mihajlik, P.: A bilingual study on the prediction of morph-based improvement. In: Proceedings of the 4th International Workshop on Spoken Language Technologies for Under-resourced Languages SLTU, St. Petersburg, Russia (2014)"},{"key":"11_CR32","unstructured":"The Department of General Linguistics, University of Helsinki; The University of Eastern Finland; CSC - IT Center for Science Ltd"},{"key":"11_CR33","unstructured":"Vaic\u0306i\u016bnas, A.: Statistical language models of Lithuanian and their application to very large vocabulary speech recognition. Summary of Doctoral dissertation. Vytautas Magnus University, Kaunas (2006)"},{"key":"11_CR34","first-page":"565","volume":"15","author":"A Vaic\u0306i\u016bnas","year":"2004","unstructured":"Vaic\u0306i\u016bnas, A., Kaminskas, V.: Statistical language models of Lithuanian based on word clustering and morphological decomposition. Inform. (Lith. Acad. Sci.) 15, 565\u2013580 (2004)","journal-title":"Inform. (Lith. Acad. Sci.)"},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Varjokallio, M., Kurimo, M.: A word-level token-passing decoder for subword n-gram LVCSR. In: Proceedings of the IEEE Workshop on Spoken Language Technology, South Lake Tahoe, USA(2014)","DOI":"10.1109\/SLT.2014.7078624"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Varjokallio, M., Kurimo, M., Virpioja, S.: Learning a subword vocabulary based on unigram likelihood. In: Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Republic (2013)","DOI":"10.1109\/ASRU.2013.6707697"},{"key":"11_CR37","doi-asserted-by":"crossref","unstructured":"Whittaker, E., Woodland, P.: Efficient class-based language modelling for very large vocabularies. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Salt Lake City, USA (2001)","DOI":"10.1109\/ICASSP.2001.940889"},{"key":"11_CR38","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/S0885-2308(02)00047-5","volume":"17","author":"E Whittaker","year":"2003","unstructured":"Whittaker, E., Woodland, P.: Language modelling for Russian and English using words and classes. Comput. Speech Lang. 17, 87\u2013104 (2003)","journal-title":"Comput. Speech Lang."},{"key":"11_CR39","unstructured":"Young, S.J., Russell, N.H., Thornton, J.H.S.: Token passing: a simple conceptual model for connected speech recognition system. Technical report, Cambridge University Engineering Department (1989)"}],"container-title":["Lecture Notes in Computer Science","Statistical Language and Speech Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-45925-7_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,8]],"date-time":"2022-07-08T21:46:20Z","timestamp":1657316780000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-45925-7_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319459240","9783319459257"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-45925-7_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}