{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,9]],"date-time":"2024-08-09T23:08:38Z","timestamp":1723244918964},"reference-count":34,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2019,12,1]]},"DOI":"10.1587\/transinf.2018edp7242","type":"journal-article","created":{"date-parts":[[2019,12,2]],"date-time":"2019-12-02T15:48:45Z","timestamp":1575301725000},"page":"2557-2567","source":"Crossref","is-referenced-by-count":7,"title":["Latent Words Recurrent Neural Network Language Models for Automatic Speech Recognition"],"prefix":"10.1587","volume":"E102.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":"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 Proc. IEEE, vol.88, no.8, 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, pp.403-434, 2001. 10.1006\/csla.2001.0174","DOI":"10.1006\/csla.2001.0174"},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] R. Masumura, T. Asami, T. Oba, H. Masataki, S. Sakauchi, and A. Ito, \u201cInvestigation of combining various major language model technologies including data expansion and adaptation,\u201d IEICE Trans. Inf. & Syst., vol.E99-D, no.10, pp.2452-2461, 2016. 10.1587\/transinf.2016slp0013","DOI":"10.1587\/transinf.2016SLP0013"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] R. Rosenfeld, \u201cA maximum entropy approach to adaptive statistical language modeling,\u201d Computer Speech & Language, vol.10, no.3, pp.187-228, 1996. 10.1006\/csla.1996.0011","DOI":"10.1006\/csla.1996.0011"},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] G. Potamianos and F. Jelinek, \u201cA study of n-gram and decision tree letter language modeling methods,\u201d Speech Communication, vol.24, no.3, pp.171-192, 1998. 10.1016\/s0167-6393(98)00018-1","DOI":"10.1016\/S0167-6393(98)00018-1"},{"key":"6","unstructured":"[6] P. Xu and F. Jelinek, \u201cRandom forests in language modeling,\u201d Proc. EMNLP 2004, pp.325-332, 2004."},{"key":"7","unstructured":"[7] Y. Bengio, R. Ducharme, P. Vincent, and C. Jauvin, \u201cA neural probabilistic language model,\u201d Journal of Machine Learning Research, vol.3, pp.1137-1155, 2003."},{"key":"8","doi-asserted-by":"publisher","unstructured":"[8] H. Schwenk, \u201cContinuous space language models,\u201d Computer Speech & Language, vol.21, no.3, pp.492-518, 2007. 10.1016\/j.csl.2006.09.003","DOI":"10.1016\/j.csl.2006.09.003"},{"key":"9","unstructured":"[9] E. Arisoy, T.N. Sainath, B. Kingsbury, and B. Ramabhadran, \u201cDeep neural network language models,\u201d Proc. NAACL-HLT 2012, pp.20-28, 2012."},{"key":"10","unstructured":"[10] T. Mikolov, M. Karafiat, L. Burget, J. Cernocky, and S. Khudanpur, \u201cRecurrent neural network based language model,\u201d Proc. Interspeech, pp.1045-1048, 2010."},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] T. Mikolov, S.K. Stefan, 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":"12","doi-asserted-by":"crossref","unstructured":"[12] Y. Su, \u201cBayesian class-based language models,\u201d Proc. ICASSP 2011, pp.5564-5567, 2011. 10.1109\/icassp.2011.5947620","DOI":"10.1109\/ICASSP.2011.5947620"},{"key":"13","doi-asserted-by":"publisher","unstructured":"[13] J.-T. Chien and C.-H. Chueh, \u201cDirichlet class language models for speech recognition,\u201d IEEE Transactions on Audio, Speech and Language Processing, vol.19, no.3, pp.1352-1365, 2011. 10.1109\/tasl.2010.2050717","DOI":"10.1109\/TASL.2010.2050717"},{"key":"14","doi-asserted-by":"publisher","unstructured":"[14] 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":"15","doi-asserted-by":"crossref","unstructured":"[15] 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":"16","unstructured":"[16] 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":"17","doi-asserted-by":"publisher","unstructured":"[17] 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 Trans. Inf. & Syst., vol.E99-D, no.10, pp.2462-2470, 2016. 10.1587\/transinf.2016slp0014","DOI":"10.1587\/transinf.2016SLP0014"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] T. Mikolov and G. Zweig, \u201cContext dependent recurrent neural network language model,\u201d Proc. SLT, pp.234-239, 2012. 10.1109\/slt.2012.6424228","DOI":"10.1109\/SLT.2012.6424228"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] X. Liu, X. Chen, M.J.F. Gales, and P.C. Woodland, \u201cParaphrastic recurrent neural network language models,\u201d Proc. ICASSP, pp.5406-5410, 2015. 10.1109\/icassp.2015.7179004","DOI":"10.1109\/ICASSP.2015.7179004"},{"key":"20","unstructured":"[20] R. Masumura, T. Asami, T. Oba, H. Masataki, S. Sakauchi, and A. Ito, \u201cLatent words recurrent neural network language models,\u201d Proc. INTERSPEECH, pp.2380-2384, 2015."},{"key":"21","unstructured":"[21] J.T. Goodman, \u201cClasses for fast maximum entropy training,\u201d Proc. ICASSP, pp.561-564, 2001. 10.1109\/icassp.2001.940893"},{"key":"22","unstructured":"[22] F. Morin and Y. Bengio, \u201cHierarchical probabilistic neural network language model,\u201d Proc. AISTATS, pp.246-252, 2005."},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] Y.W. Teh, \u201cA hierarchical Bayesian language model based on Pitman-Yor processes,\u201d Proc. ACL, pp.985-992, 2006. 10.3115\/1220175.1220299","DOI":"10.3115\/1220175.1220299"},{"key":"24","doi-asserted-by":"publisher","unstructured":"[24] D.J.C. MacKay and L.C. Peto, \u201cA hierarchical dirichlet language model,\u201d Natural language engineering, vol.1, pp.289-308, 1995. 10.1017\/s1351324900000218","DOI":"10.1017\/S1351324900000218"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] M.P. Marcus, M.A. Marcinkiewicz, and B. Santorini, \u201cBuilding a large annotated corpus of English: The penn treebank,\u201d Computational Linguistics, vol.19, pp.313-330, 1993.","DOI":"10.21236\/ADA273556"},{"key":"26","doi-asserted-by":"publisher","unstructured":"[26] S.F. Chen and J. Goodman, \u201cAn empirical study of smoothing techniques for language modeling,\u201d Computer Speech & Language, vol.13, no.4, pp.359-383, 1999. 10.1006\/csla.1999.0128","DOI":"10.1006\/csla.1999.0128"},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] Y.W. Teh, \u201cA hierarchical Bayesian language model based on Pitman-Yor processes,\u201d Proc. COLING-ACL, pp.985-992, 2006. 10.3115\/1220175.1220299","DOI":"10.3115\/1220175.1220299"},{"key":"28","unstructured":"[28] A. Stolcke, \u201cEntropy-based pruning of backoff language models,\u201d Proc. DARPA Broadcast News Transcription and Understanding Workshop, pp.270-274, 1998."},{"key":"29","unstructured":"[29] K. Maekawa, H. Koiso, S. Furui, and H. Isahara, \u201cSpontaneous speech corpus of Japanese,\u201d Proc. LREC, pp.947-952, 2000."},{"key":"30","unstructured":"[30] G. Hinton, L. Deng, D. Yu, G. Dahl, A.R. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. Sainath, and B. Kingsbury, \u201cDeep neural networks for acoustic modeling in speech recognition,\u201d Signal Processing Magazine, pp.1-27, 2012."},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] M. Sundermeyer, R. Schluter, and H. Ney, \u201cLSTM neural networks for language modeling,\u201d Proc. INTERSPEECH, pp.194-197, 2012.","DOI":"10.21437\/Interspeech.2012-65"},{"key":"32","doi-asserted-by":"publisher","unstructured":"[32] M. Sundermeyer, H. Ney, and R. Schluter, \u201cFrom feedforward to recurrent LSTM neural networks for language models,\u201d IEEE\/ACM Transactions of Audio, Speech and Language processing, vol.23, no.3, pp.517-529, 2015. 10.1109\/taslp.2015.2400218","DOI":"10.1109\/TASLP.2015.2400218"},{"key":"33","unstructured":"[33] 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":"34","doi-asserted-by":"publisher","unstructured":"[34] R. Masumura, T. Asami, T. Oba, H. Masataki, S. Sakauchi, and A. Ito, \u201cDomain adaptation based on mixture of latent words language models for automatic speech recognition,\u201d IEICE Trans. Inf. & Syst., vol.E101-D, no.6, pp.1581-1590, 2018. 10.1587\/transinf.2017edp7210","DOI":"10.1587\/transinf.2017EDP7210"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E102.D\/12\/E102.D_2018EDP7242\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,7]],"date-time":"2022-10-07T10:51:18Z","timestamp":1665139878000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E102.D\/12\/E102.D_2018EDP7242\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,1]]},"references-count":34,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2019]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2018edp7242","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12,1]]}}}