{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T04:13:20Z","timestamp":1751688800940,"version":"3.41.0"},"reference-count":34,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2018,6,1]]},"DOI":"10.1587\/transinf.2017edp7210","type":"journal-article","created":{"date-parts":[[2018,5,31]],"date-time":"2018-05-31T22:50:16Z","timestamp":1527807016000},"page":"1581-1590","source":"Crossref","is-referenced-by-count":4,"title":["Domain Adaptation Based on Mixture of Latent Words Language Models for Automatic Speech Recognition"],"prefix":"10.1587","volume":"E101.D","author":[{"given":"Ryo","family":"MASUMURA","sequence":"first","affiliation":[{"name":"NTT Media Intelligence Laboratories, NTT Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taichi","family":"ASAMI","sequence":"additional","affiliation":[{"name":"NTT Media Intelligence Laboratories, NTT Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takanobu","family":"OBA","sequence":"additional","affiliation":[{"name":"NTT Media Intelligence Laboratories, NTT Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hirokazu","family":"MASATAKI","sequence":"additional","affiliation":[{"name":"NTT Media Intelligence Laboratories, NTT Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sumitaka","family":"SAKAUCHI","sequence":"additional","affiliation":[{"name":"NTT Media Intelligence Laboratories, NTT Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akinori","family":"ITO","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering, Tohoku University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] R. Rosenfeld, \u201cTwo decades of statistical language modeling: Where do we go from here?,\u201d Proceedings of the IEEE, vol.88, pp.1270-1278, 2000. 10.1109\/5.880083","DOI":"10.1109\/5.880083"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] J.T. Goodman, \u201cA bit of progress in language modeling,\u201d Computer Speech & Language, vol.15, no.4, pp.403-434, 2001. 10.1006\/csla.2001.0174","DOI":"10.1006\/csla.2001.0174"},{"key":"3","unstructured":"[3] T. Brants, A.C. Popat, P. Xu, F.J. Och, and J. Dean, \u201cLarge language models in machine translation,\u201d Proc. ACL, pp.858-867, 2007."},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] J.R. Bellegarda, \u201cStatistical language model adaptation: Review and perspectives,\u201d Speech Communication, vol.42, no.1, pp.93-108, 2004. 10.1016\/j.specom.2003.08.002","DOI":"10.1016\/j.specom.2003.08.002"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] P. Koehn and J. Schroeder, \u201cExperiments in domain adaptation for statistical machine translation,\u201d Proc. Second Workshop on Statistical Machine Translation, pp.224-227, 2007. 10.3115\/1626355.1626388","DOI":"10.3115\/1626355.1626388"},{"key":"6","doi-asserted-by":"publisher","unstructured":"[6] S. Katz, \u201cEstimation of probabilities from sparse data for the language model component of a speech recognizer,\u201d IEEE Transactions on Audio, Speech and Language Processing, vol.35, no.3, pp.400-401, 1987. 10.1109\/tassp.1987.1165125","DOI":"10.1109\/TASSP.1987.1165125"},{"key":"7","doi-asserted-by":"publisher","unstructured":"[7] R.M. Iyer and M. Ostendorf, \u201cModeling long distance dependence in language: topic mixtures versus dynamic cache models,\u201d IEEE Transactions on Speech and Audio Processing, vol.7, no.1, pp.30-39, 1999. 10.1109\/89.736328","DOI":"10.1109\/89.736328"},{"key":"8","doi-asserted-by":"publisher","unstructured":"[8] R. Iyer, M. Ostendorf, and H. Gish, \u201cUsing out-of-domain data to improve in-domain language models,\u201d IEEE Signal Process. Lett., vol.4, no.8, pp.221-223, 1997. 10.1109\/97.611282","DOI":"10.1109\/97.611282"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] G. Foster and R. Kuhn, \u201cMixture-model adaptation for SMT,\u201d Proc. Second Workshop on Statistical Machine Translation, pp.128-135, 2007. 10.3115\/1626355.1626372","DOI":"10.3115\/1626355.1626372"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] B.-J. Hsu, \u201cGeneralized linear interpolation of language models,\u201d Proc. ASRU, pp.136-140, 2007. 10.1109\/asru.2007.4430098","DOI":"10.1109\/ASRU.2007.4430098"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] X. Liu, M.J.F. Gales, and P.C. Woodland, \u201cContext dependent language model adaptation,\u201d Proc. INTERSPEECH, pp.837-840, 2008.","DOI":"10.21437\/Interspeech.2008-254"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] T. Mikolov, S. Kombrink, L. Burget, J. Cernocky, and S. Khudanpur, \u201cExtensions of recurrent neural network language model,\u201d Proc. ICASSP, pp.5528-5531, 2011. 10.1109\/icassp.2011.5947611","DOI":"10.1109\/ICASSP.2011.5947611"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] Y. Shi, M. Larson, and C.M. Jonker, \u201cK-component recurrent neural network language models using curriculum learning,\u201d Proc. ASRU, pp.1-6, 2013. 10.1109\/asru.2013.6707696","DOI":"10.1109\/ASRU.2013.6707696"},{"key":"14","doi-asserted-by":"publisher","unstructured":"[14] Y. Shi, M. Larson, and C.M. Jonker, \u201cRecurrent neural network language model adaptation with curriculum learning,\u201d Computer Speech & Language, vol.33, no.1, pp.136-154, 2015. 10.1016\/j.csl.2014.11.004","DOI":"10.1016\/j.csl.2014.11.004"},{"key":"15","doi-asserted-by":"publisher","unstructured":"[15] K. Deschacht, J.D. Belder, and M.-F. Moens, \u201cThe latent words language model,\u201d Computer Speech & Language, vol.26, no.5, pp.384-409, 2012. 10.1016\/j.csl.2012.04.001","DOI":"10.1016\/j.csl.2012.04.001"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] R. Masumura, H. Masataki, T. Oba, O. Yoshioka, and S. Takahashi, \u201cUse of latent words language models in ASR: a sampling-based implementation,\u201d Proc. ICASSP, pp.8445-8449, 2013. 10.1109\/icassp.2013.6639313","DOI":"10.1109\/ICASSP.2013.6639313"},{"key":"17","unstructured":"[17] R. Masumura, T. Oba, H. Masataki, O. Yoshioka, and S. Takahashi, \u201cViterbi decoding for latent words language models using Gibbs sampling,\u201d Proc. INTERSPEECH, pp.3429-3433, 2013."},{"key":"18","doi-asserted-by":"publisher","unstructured":"[18] R. Masumura, T. Adami, T. Oba, H. Masataki, S. Sakauchi, and S. Takahashi, \u201cN-gram approximation of latent words language models for domain robust automatic speech recognition,\u201d IEICE Transaction. on Information and Systems, vol.E99-D, no.10, pp.2462-2470, 2016. 10.1587\/transinf.2016slp0014","DOI":"10.1587\/transinf.2016SLP0014"},{"key":"19","unstructured":"[19] S. Goldwater and T. Griffiths, \u201cA fully Bayesian approach to unsupervised part-of-speech tagging,\u201d Proc. ACL, pp.744-751, 2007."},{"key":"20","unstructured":"[20] P. Blunsom and T. Cohn, \u201cA hierarchical Pitman-Yor process HMM for unsupervised part of speech induction,\u201d Proc. ACL, pp.865-874, 1996."},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] T.R. Niesler and P.C. Woodland, \u201cCombination word-based and category-based language models,\u201d Proc. ICSLP, vol.1, pp.220-223, 1996. 10.1109\/icslp.1996.607081","DOI":"10.1109\/ICSLP.1996.607081"},{"key":"22","unstructured":"[22] R.C. Moore and W. Lewis, \u201cIntelligent selection of language model training data,\u201d Proc. ACL, pp.220-224, 2010."},{"key":"23","unstructured":"[23] F. Jelinek and R.L. Mercer, \u201cInterpolated estimation of Markov source parameters from sparse data,\u201d pattern Recognition in Practice, pp.381-397, 1980."},{"key":"24","doi-asserted-by":"publisher","unstructured":"[24] G. Casella and E.I. George, \u201cExplaining the Gibbs sampler,\u201d The American Statistician, vol.46, no.3, pp.167-174, 1992. 10.1080\/00031305.1992.10475878","DOI":"10.1080\/00031305.1992.10475878"},{"key":"25","unstructured":"[25] R. Masumura, T. Asami, T. Oba, H. Masataki, and S. Sakauchi, \u201cMixture of latent words language models for domain adaptation,\u201d Porc. INTERPSEECH, pp.1425-1429, 2014."},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] A. Stolcke, \u201cSRILM-an extensible language modeling toolkit,\u201d In Proc. ICSLP, vol.2, pp.901-904, 2002.","DOI":"10.21437\/ICSLP.2002-303"},{"key":"27","unstructured":"[27] K. Maekawa, H. Koiso, S. Furui, and H. Isahara, \u201cSpontaneous speech corpus of Japanese,\u201d Proc. LREC, pp.947-952, 2000."},{"key":"28","doi-asserted-by":"publisher","unstructured":"[28] G. Hinton, L. Deng, D. Yu, G.E. Dahl, A. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T.N. Sainath, and B. Kingsbury, \u201cDeep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups,\u201d Signal Processing Magazine, vol.29, no.6, pp.82-97, 2012. 10.1109\/msp.2012.2205597","DOI":"10.1109\/MSP.2012.2205597"},{"key":"29","doi-asserted-by":"publisher","unstructured":"[29] T. Hori, C. Hori, Y. Minami, and A. Nakamura, \u201cEfficient WFST-based one-pass decoding with on-the-fly hypothesis rescoring in extremely large vocabulary continuous speech recognition,\u201d IEEE transactions on Audio, Speech and Language Processing, vol.15, no.4, pp.1352-1365, 2007. 10.1109\/tasl.2006.889790","DOI":"10.1109\/TASL.2006.889790"},{"key":"30","unstructured":"[30] H. Masataki, D. Shibata, Y. Nakazawa, S. Kobashikawa, A. Ogawa, and K. Ohtsuki, \u201cVoiceRex spontaneous speech recognition technology for contact-center conversations,\u201d NTT Technical Review, vol.5, no.1, pp.22-27, 2007."},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] T. Fuchi and S. Takagi, \u201cJapanese morphological analyzer using word co-occurrence: JTAG,\u201d Proc. COLING\/ACL, pp.409-413, 1998. 10.3115\/980451.980915","DOI":"10.3115\/980845.980915"},{"key":"32","doi-asserted-by":"crossref","unstructured":"[32] S. Huang and S. Renals, \u201cHierarchical Pitman-Yor language models for ASR in meetings,\u201d Proc. ASRU, pp.124-129, 2007.","DOI":"10.1109\/ASRU.2007.4430096"},{"key":"33","unstructured":"[33] A. Stolcke, \u201cEntropy-based pruning of backoff language models,\u201d In Proc. DARPA Broadcast News Transcription and Understanding Workshop, pp.270-274, 1998."},{"key":"34","unstructured":"[34] R. Masumura, S. Hahm, and A. Ito, \u201cLanguage model expansion using webdata for spoken document retrieval,\u201d Proc. INTERSPEECH, pp.2133-2136, 2011."}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E101.D\/6\/E101.D_2017EDP7210\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T22:37:56Z","timestamp":1751668676000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E101.D\/6\/E101.D_2017EDP7210\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,1]]},"references-count":34,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2018]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2017edp7210","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"type":"print","value":"0916-8532"},{"type":"electronic","value":"1745-1361"}],"subject":[],"published":{"date-parts":[[2018,6,1]]}}}