{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T23:29:27Z","timestamp":1762298967765},"reference-count":47,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2019,3,1]]},"DOI":"10.1587\/transinf.2018edp7222","type":"journal-article","created":{"date-parts":[[2019,2,28]],"date-time":"2019-02-28T22:38:48Z","timestamp":1551393528000},"page":"598-608","source":"Crossref","is-referenced-by-count":4,"title":["Feature Based Domain Adaptation for Neural Network Language Models with Factorised Hidden Layers"],"prefix":"10.1587","volume":"E102.D","author":[{"given":"Michael","family":"HENTSCHEL","sequence":"first","affiliation":[{"name":"Nara Institute of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"DELCROIX","sequence":"additional","affiliation":[{"name":"NTT Communication Science Laboratories, NTT Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsunori","family":"OGAWA","sequence":"additional","affiliation":[{"name":"NTT Communication Science Laboratories, NTT Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoharu","family":"IWATA","sequence":"additional","affiliation":[{"name":"NTT Communication Science Laboratories, NTT Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomohiro","family":"NAKATANI","sequence":"additional","affiliation":[{"name":"NTT Communication Science Laboratories, NTT Corporation"}],"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.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":"3","doi-asserted-by":"crossref","unstructured":"[3] Y.C. Tam and T. Schultz, \u201cDynamic language model adaptation using variational bayes inference,\u201d Ninth European Conference on Speech Communication and Technology, 2005.","DOI":"10.21437\/Interspeech.2005-4"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] A. Heidel, H.A. Chang, and L.S. Lee, \u201cLanguage model adaptation using latent dirichlet allocation and an efficient topic inference algorithm,\u201d Eighth Annual Conference of the International Speech Communication Association, 2007.","DOI":"10.21437\/Interspeech.2007-268"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] Y. Liu and F. Liu, \u201cUnsupervised language model adaptation via topic modeling based on named entity hypotheses,\u201d IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.4921-4924, IEEE, 2008. 10.1109\/icassp.2008.4518761","DOI":"10.1109\/ICASSP.2008.4518761"},{"key":"6","doi-asserted-by":"publisher","unstructured":"[6] S. Watanabe, T. Iwata, T. Hori, A. Sako, and Y. Ariki, \u201cTopic tracking language model for speech recognition,\u201d Computer Speech & Language, vol.25, no.2, pp.440-461, 2011. 10.1016\/j.csl.2010.07.006","DOI":"10.1016\/j.csl.2010.07.006"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] M.A. Haidar and D. O'Shaughnessy, \u201cTopic n-gram count language model adaptation for speech recognition,\u201d Spoken Language Technology Workshop (SLT), pp.165-169, IEEE, 2012. 10.1109\/slt.2012.6424216","DOI":"10.1109\/SLT.2012.6424216"},{"key":"8","doi-asserted-by":"publisher","unstructured":"[8] R. Rosenfeld, \u201cA maximum entropy approach to adaptive statistical language modelling,\u201d Computer Speech and Language, vol.10, no.3, pp.187-228, 1996. 10.1006\/csla.1996.0011","DOI":"10.1006\/csla.1996.0011"},{"key":"9","unstructured":"[9] A.L. Berger, V.J.D. Pietra, and S.A.D. Pietra, \u201cA maximum entropy approach to natural language processing,\u201d Computational linguistics, vol.22, no.1, pp.39-71, 1996."},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] S. Della Pietra, V. Della Pietra, R.L. Mercer, and S. Roukos, \u201cAdaptive language modeling using minimum discriminant estimation,\u201d IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.633-636, IEEE, 1992. 10.1109\/icassp.1992.225829","DOI":"10.1109\/ICASSP.1992.225829"},{"key":"11","doi-asserted-by":"publisher","unstructured":"[11] S. Khudanpur and J. Wu, \u201cMaximum entropy techniques for exploiting syntactic, semantic and collocational dependencies in language modeling,\u201d Computer Speech & Language, vol.14, no.4, pp.355-372, 2000. 10.1006\/csla.2000.0149","DOI":"10.1006\/csla.2000.0149"},{"key":"12","unstructured":"[12] T. Alum\u00e4e and M. Kurimo, \u201cDomain adaptation of maximum entropy language models,\u201d ACL, pp.301-306, Association for Computational Linguistics, 2010."},{"key":"13","unstructured":"[13] 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":"14","unstructured":"[14] T. Mikolov, M. Karafi\u00e1t, L. Burget, J. \u010cernock\u1ef3, and S.Khudanpur, \u201cRecurrent neural network based language model,\u201dINTERSPEECH, pp.1045-1048, 2010."},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] T. Mikolov, S. Kombrink, L. Burget, J. \u010cernock\u1ef3, and S. Khudanpur, \u201cExtensions of recurrent neural network language model,\u201d IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.5528-5531, IEEE, 2011. 10.1109\/icassp.2011.5947611","DOI":"10.1109\/ICASSP.2011.5947611"},{"key":"16","doi-asserted-by":"publisher","unstructured":"[16] Y. Bengio, P. Simard, and P. Frasconi, \u201cLearning long-term dependencies with gradient descent is difficult,\u201d IEEE Trans. Neural Netw., vol.5, no.2, pp.157-166, 1994. 10.1109\/72.279181","DOI":"10.1109\/72.279181"},{"key":"17","doi-asserted-by":"publisher","unstructured":"[17] S. Hochreiter and J. Schmidhuber, \u201cLong Short-Term Memory,\u201d Neural computation, vol.9, no.8, pp.1735-1780, 1997. 10.1162\/neco.1997.9.8.1735","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] M. Sundermeyer, R. Schl\u00fcter, and H. Ney, \u201cLSTM neural networks for language modeling,\u201d INTERSPEECH, pp.194-197, 2012.","DOI":"10.21437\/Interspeech.2012-65"},{"key":"19","unstructured":"[19] D.M. Blei, A.Y. Ng, and M.I. Jordan, \u201cLatent Dirichlet allocation,\u201d Journal of machine Learning research, vol.3, pp.993-1022, 2003."},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] S.R. Gangireddy, P. Swietojanski, P. Bell, and S. Renals, \u201cUnsupervised adaptation of recurrent neural network language models,\u201d INTERSPEECH, pp.2333-2337, 2016.","DOI":"10.21437\/Interspeech.2016-1342"},{"key":"21","doi-asserted-by":"publisher","unstructured":"[21] M. Delcroix, K. Kinoshita, A. Ogawa, C. Huemmer, and T. Nakatani, \u201cContext adaptive neural network based acoustic models for rapid adaptation,\u201d IEEE\/ACM Trans. Audio, Speech, Language Process., vol.26, no.5, pp.895-908, May 2018. 10.1109\/taslp.2018.2798821","DOI":"10.1109\/TASLP.2018.2798821"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] K. \u017dmol\u00edkov\u00e1, M. Delcroix, K. Kinoshita, T. Higuchi, A. Ogawa, and T. Nakatani, \u201cSpeaker-aware neural network based beamformer for speaker extraction in speech mixtures,\u201d INTERSPEECH, pp.2655-2659, 2017. 10.21437\/interspeech.2017-667","DOI":"10.21437\/Interspeech.2017-667"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] M.P. Marcus, M.A. Marcinkiewicz, and B. Santorini, \u201cBuilding a large annotated corpus of english: The Penn Treebank,\u201d Computational linguistics, vol.19, no.2, pp.313-330, 1993.","DOI":"10.21236\/ADA273556"},{"key":"24","unstructured":"[24] A. Rousseau, P. Del\u00e9glise, and Y. Esteve, \u201cTED-LIUM: an automatic speech recognition dedicated corpus,\u201d LREC, pp.125-129, 2012."},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] W. Williams, N. Prasad, D. Mrva, T. Ash, and T. Robinson, \u201cScaling recurrent neural network language models,\u201d IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.5391-5395, IEEE, 2015.","DOI":"10.1109\/ICASSP.2015.7179001"},{"key":"26","doi-asserted-by":"crossref","unstructured":"[26] J. Park, X. Liu, M.J. Gales, and P.C. Woodland, \u201cImproved neural network based language modelling and adaptation,\u201dINTERSPEECH, 2010.","DOI":"10.21437\/Interspeech.2010-342"},{"key":"27","unstructured":"[27] T. Alum\u00e4e, \u201cMulti-domain neural network language model,\u201dINTERSPEECH, vol.13, pp.2182-2186, 2013."},{"key":"28","unstructured":"[28] O. Tilk and T. Alum\u00e4e, \u201cMulti-domain recurrent neural network language model for medical speech recognition,\u201d Baltic HLT, pp.149-152, 2014."},{"key":"29","doi-asserted-by":"publisher","unstructured":"[29] R. Gemello, F. Mana, S. Scanzio, P. Laface, and R. De Mori, \u201cLinear hidden transformations for adaptation of hybrid ANN\/HMM models,\u201d Speech Communication, vol.49, no.10, pp.827-835, 2007. 10.1016\/j.specom.2006.11.005","DOI":"10.1016\/j.specom.2006.11.005"},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] P. Bell, M.J. Gales, T. Hain, J. Kilgour, P. Lanchantin, X. Liu, A. McParland, S. Renals, O. Saz, M. Wester, et al., \u201cThe MGB challenge: Evaluating multi-genre broadcast media recognition,\u201d IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp.687-693, IEEE, 2015.","DOI":"10.1109\/ASRU.2015.7404863"},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] P. Swietojanski and S. Renals, \u201cLearning hidden unit contributions for unsupervised speaker adaptation of neural network acoustic models,\u201d Spoken Language Technology Workshop (SLT), pp.171-176, IEEE, 2014. 10.1109\/slt.2014.7078569","DOI":"10.1109\/SLT.2014.7078569"},{"key":"32","doi-asserted-by":"crossref","unstructured":"[32] L. Samarakoon and K.C. Sim, \u201cSubspace LHUC for fast adaptation of deep neural network acoustic models,\u201d INTERSPEECH, pp.1593-1597, 2016. 10.21437\/interspeech.2016-1249","DOI":"10.21437\/Interspeech.2016-1249"},{"key":"33","doi-asserted-by":"crossref","unstructured":"[33] T. Mikolov and G. Zweig, \u201cContext dependent recurrent neural network language model,\u201d Spoken Language Technology Workshop (SLT), pp.234-239, IEEE, 2012.","DOI":"10.1109\/SLT.2012.6424228"},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] X. Chen, T. Tan, X. Liu, P. Lanchantin, M. Wan, M.J. Gales, and P.C. Woodland, \u201cRecurrent neural network language model adaptation for multi-genre broadcast speech recognition,\u201d INTERSPEECH, 2015.","DOI":"10.21437\/Interspeech.2015-696"},{"key":"35","doi-asserted-by":"crossref","unstructured":"[35] D. Soutner and L. M\u00fcller, \u201cApplication of LSTM neural networks in language modelling,\u201d International Conference on Text, Speech and Dialogue, pp.105-112, Springer, 2013.","DOI":"10.1007\/978-3-642-40585-3_14"},{"key":"36","unstructured":"[36] J. Zhang, X. Wu, A. Way, and Q. Liu, \u201cFast gated neural domain adaptation: Language model as a case study,\u201d International Conference on Computational Linguistics (COLING), pp.1386-1397, 2016."},{"key":"37","doi-asserted-by":"crossref","unstructured":"[37] M. Sundermeyer, H. Ney, and R. Schl\u00fcter, \u201cFrom feedforward to recurrent LSTM neural networks for language modeling,\u201d IEEE\/ACM Trans. Audio, Speech, Language Process., vol.23, no.3, pp.517-529, 2015.","DOI":"10.1109\/TASLP.2015.2400218"},{"key":"38","doi-asserted-by":"crossref","unstructured":"[38] S. Deena, M. Hasan, M. Doulaty, O. Saz, and T. Hain, \u201cCombining feature and model-based adaptation of RNNLMs for multi-genre broadcast speech recognition,\u201d INTERSPEECH, pp.2343-2347, 2016. 10.21437\/interspeech.2016-480","DOI":"10.21437\/Interspeech.2016-480"},{"key":"39","doi-asserted-by":"crossref","unstructured":"[39] M. Delcroix, K. Kinoshita, C. Yu, A. Ogawa, T. Yoshioka, and T. Nakatani, \u201cContext adaptive deep neural networks for fast acoustic model adaptation in noisy conditions,\u201d IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.5270-5274, IEEE, 2016.","DOI":"10.1109\/ICASSP.2016.7472683"},{"key":"40","unstructured":"[40] D. Povey, A. Ghoshal, G. Boulianne, L. Burget, O. Glembek, N. Goel, M. Hannemann, P. Motlicek, Y. Qian, P. Schwarz, J. Silovsky, G. Stemmer, and K. Vesely, \u201cThe Kaldi Speech Recognition Toolkit,\u201d IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), IEEE, Dec. 2011."},{"key":"41","unstructured":"[41] M. Federico, L. Bentivogli, P. Michael, and S. Sebastian, \u201cOverview of the IWSLT 2011 evaluation campaign,\u201d International Workshop on Spoken Language Translation (IWSLT), 2011."},{"key":"42","unstructured":"[42] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J.Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, \u201cScikit-learn: Machine Learning in Python,\u201d Journal of Machine Learning Research, vol.12, pp.2825-2830, 2011."},{"key":"43","unstructured":"[43] J. Duchi, E. Hazan, and Y. Singer, \u201cAdative subgradient methods for online learning and stochastic optimization,\u201d Journal of Machine Learning Research, vol.12, pp.2121-2159, 2011."},{"key":"44","unstructured":"[44] G.E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R.R. Salakhutdinov, \u201cImproving neural networks by preventing co-adaptation of feature detectors,\u201d arXiv preprint arXiv:1207.0580, 2012."},{"key":"45","unstructured":"[45] S. Tokui, K. Oono, S. Hido, and J. Clayton, \u201cChainer: a next-generation open source framework for deep learning,\u201d Workshop on Machine Learning Systems (LearningSys) in the Twenty-ninth Annual Conference on Neural Information Processing (NIPS), 2015."},{"key":"46","doi-asserted-by":"crossref","unstructured":"[46] R. Kneser and H. Ney, \u201cImproved backing-off for m-gram language modeling,\u201d IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol.1, pp.181-184, IEEE, 1995. 10.1109\/icassp.1995.479394","DOI":"10.1109\/ICASSP.1995.479394"},{"key":"47","doi-asserted-by":"crossref","unstructured":"[47] A. Stolcke, \u201cSRILM-an extensible language modeling toolkit,\u201d International Conference on Speech and Language Processing, pp.901-904, 2002.","DOI":"10.21437\/ICSLP.2002-303"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E102.D\/3\/E102.D_2018EDP7222\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T21:33:21Z","timestamp":1663018401000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E102.D\/3\/E102.D_2018EDP7222\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3,1]]},"references-count":47,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2018edp7222","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,3,1]]}}}