{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:35:40Z","timestamp":1765546540523},"reference-count":52,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. &amp; Syst."],"published-print":{"date-parts":[[2020,2,1]]},"DOI":"10.1587\/transinf.2019edp7040","type":"journal-article","created":{"date-parts":[[2020,1,31]],"date-time":"2020-01-31T17:09:48Z","timestamp":1580490588000},"page":"435-449","source":"Crossref","is-referenced-by-count":1,"title":["Recurrent Neural Network Compression Based on Low-Rank Tensor Representation"],"prefix":"10.1587","volume":"E103.D","author":[{"given":"Andros","family":"TJANDRA","sequence":"first","affiliation":[{"name":"Augmented Human Communication Lab, Nara Institute of Science and Technology"},{"name":"RIKEN, Center for Advanced Intelligence Project AIP"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sakriani","family":"SAKTI","sequence":"additional","affiliation":[{"name":"Augmented Human Communication Lab, Nara Institute of Science and Technology"},{"name":"RIKEN, Center for Advanced Intelligence Project AIP"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"NAKAMURA","sequence":"additional","affiliation":[{"name":"Augmented Human Communication Lab, Nara Institute of Science and Technology"},{"name":"RIKEN, Center for Advanced Intelligence Project AIP"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] J.L. Elman, \u201cFinding structure in time,\u201d Cognitive science, vol.14, no.2, pp.179-211, 1990. 10.1207\/s15516709cog1402_1","DOI":"10.1207\/s15516709cog1402_1"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] 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":"3","unstructured":"[3] A. Hannun, C. Case, J. Casper, B. Catanzaro, G. Diamos, E. Elsen, R. Prenger, S. Satheesh, S. Sengupta, A. Coates, et al., \u201cDeep speech: Scaling up end-to-end speech recognition,\u201d arXiv preprint arXiv:1412.5567, 2014."},{"key":"4","unstructured":"[4] D. Amodei, R. Anubhai, E. Battenberg, C. Case, J. Casper, B.Catanzaro, J. Chen, M. Chrzanowski, A. Coates, G. Diamos, et al., \u201cDeep speech 2: End-to-end speech recognition in English and Mandarin,\u201d arXiv preprint arXiv:1512.02595, 2015."},{"key":"5","unstructured":"[5] Y. Wu, M. Schuster, Z. Chen, Q.V. Le, M. Norouzi, W. Macherey, M. Krikun, Y. Cao, Q. Gao, K. Macherey, et al., \u201cGoogle&apos;s neural machine translation system: Bridging the gap between human and machine translation,\u201d arXiv preprint arXiv:1609.08144, 2016."},{"key":"6","unstructured":"[6] D. Bahdanau, K. Cho, and Y. Bengio, \u201cNeural machine translation by jointly learning to align and translate,\u201d arXiv preprint arXiv:1409.0473, 2014."},{"key":"7","unstructured":"[7] I. Sutskever, O. Vinyals, and Q.V. Le, \u201cSequence to sequence learning with neural networks,\u201d Advances in neural information processing systems, pp.3104-3112, 2014."},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] M. Schuster, \u201cSpeech recognition for mobile devices at Google,\u201d Pacific Rim International Conference on Artificial Intelligence, pp.8-10, Springer, 2010. 10.1007\/978-3-642-15246-7_3","DOI":"10.1007\/978-3-642-15246-7_3"},{"key":"9","unstructured":"[9] G. Hinton, O. Vinyals, and J. Dean, \u201cDistilling the knowledge in a neural network,\u201d arXiv preprint arXiv:1503.02531, 2015."},{"key":"10","unstructured":"[10] J. Ba and R. Caruana, \u201cDo deep nets really need to be deep?,\u201d Advances in neural information processing systems, pp.2654-2662, 2014."},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] Z. Tang, D. Wang, and Z. Zhang, \u201cRecurrent neural network training with dark knowledge transfer,\u201d 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.5900-5904, IEEE, 2016. 10.1109\/icassp.2016.7472809","DOI":"10.1109\/ICASSP.2016.7472809"},{"key":"12","unstructured":"[12] M. Denil, B. Shakibi, L. Dinh, N. de Freitas, et al., \u201cPredicting parameters in deep learning,\u201d Advances in Neural Information Processing Systems, pp.2148-2156, 2013."},{"key":"13","unstructured":"[13] A. Novikov, D. Podoprikhin, A. Osokin, and D.P. Vetrov, \u201cTensorizing neural networks,\u201d Advances in Neural Information Processing Systems, pp.442-450, 2015."},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] I.V. Oseledets, \u201cTensor-train decomposition,\u201d SIAM Journal on Scientific Computing, vol.33, no.5, pp.2295-2317, 2011. 10.1137\/090752286","DOI":"10.1137\/090752286"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] A. Tjandra, S. Sakti, and S. Nakamura, \u201cCompressing recurrent neural network with tensor train,\u201d 2017 International Joint Conference on Neural Networks (IJCNN), pp.4451-4458, IEEE, 2017. 10.1109\/ijcnn.2017.7966420","DOI":"10.1109\/IJCNN.2017.7966420"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] A. Tjandra, S. Sakti, and S. Nakamura, \u201cTensor decomposition for compressing recurrent neural network,\u201d 2018 International Joint Conference on Neural Networks (IJCNN), pp.1-8, July 2018. 10.1109\/ijcnn.2018.8489213","DOI":"10.1109\/IJCNN.2018.8489213"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] T. Mori, A. Tjandra, S. Sakti, and S. Nakamura, \u201cCompressing end-to-end ASR networks by tensor-train decomposition,\u201d Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 Sept. 2018, pp.806-810, 2018. 10.21437\/interspeech.2018-1543","DOI":"10.21437\/Interspeech.2018-1543"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] A. Graves, A.r. Mohamed, and G. Hinton, \u201cSpeech recognition with deep recurrent neural networks,\u201d 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.6645-6649, IEEE, 2013. 10.1109\/icassp.2013.6638947","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"19","doi-asserted-by":"publisher","unstructured":"[19] 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":"20","unstructured":"[20] S. Hochreiter, Y. Bengio, P. Frasconi, and J. Schmidhuber, \u201cGradient flow in recurrent nets: the difficulty of learning long-term dependencies,\u201d 2001."},{"key":"21","unstructured":"[21] Q.V. Le, N. Jaitly, and G.E. Hinton, \u201cA simple way to initialize recurrent networks of rectified linear units,\u201d arXiv preprint arXiv:1504.00941, 2015."},{"key":"22","unstructured":"[22] J. Martens and I. Sutskever, \u201cLearning recurrent neural networks with Hessian-free optimization,\u201d Proc. 28th International Conference on Machine Learning (ICML-11), pp.1033-1040, 2011."},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] A. Graves, N. Jaitly, and A.r. Mohamed, \u201cHybrid speech recognition with deep bidirectional LSTM,\u201d 2013 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp.273-278, IEEE, 2013. 10.1109\/asru.2013.6707742","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] K. Cho, B. Van Merri\u00ebnboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, \u201cLearning phrase representations using RNN encoder-decoder for statistical machine translation,\u201d arXiv preprint arXiv:1406.1078, 2014.","DOI":"10.3115\/v1\/D14-1179"},{"key":"25","unstructured":"[25] J. Chung, C. Gulcehre, K. Cho, and Y. Bengio, \u201cEmpirical evaluation of gated recurrent neural networks on sequence modeling,\u201d arXiv preprint arXiv:1412.3555, 2014."},{"key":"26","unstructured":"[26] R.A. Harshman, \u201cFoundations of the parafac procedure: Models and conditions for an \u201cexplanatory\u201d multimodal factor analysis,\u201d 1970."},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] H.A. Kiers, \u201cTowards a standardized notation and terminology in multiway analysis,\u201d Journal of chemometrics, vol.14, no.3, pp.105-122, 2000. 10.1002\/1099-128x(200005\/06)14:3%3C105::aid-cem582%3E3.0.co;2-i","DOI":"10.1002\/1099-128X(200005\/06)14:3<105::AID-CEM582>3.0.CO;2-I"},{"key":"28","doi-asserted-by":"publisher","unstructured":"[28] T.G. Kolda and B.W. Bader, \u201cTensor decompositions and applications,\u201d SIAM review, vol.51, no.3, pp.455-500, 2009. 10.1137\/07070111x","DOI":"10.1137\/07070111X"},{"key":"29","doi-asserted-by":"crossref","unstructured":"[29] L.R. Tucker, \u201cSome mathematical notes on three-mode factor analysis,\u201d Psychometrika, vol.31, no.3, pp.279-311, 1966. 10.1007\/bf02289464","DOI":"10.1007\/BF02289464"},{"key":"30","unstructured":"[30] R. Pascanu, T. Mikolov, and Y. Bengio, \u201cOn the difficulty of training recurrent neural networks,\u201d International Conference on Machine Learning, pp.1310-1318, 2013."},{"key":"31","unstructured":"[31] X. Glorot and Y. Bengio, \u201cUnderstanding the difficulty of training deep feedforward neural networks,\u201d Proc. International Conference on Artificial Intelligence and Statistics (AISTATS&apos;10), Society for Artificial Intelligence and Statistics, 2010."},{"key":"32","unstructured":"[32] N. Boulanger-lewandowski, Y. Bengio, and P. Vincent, \u201cModeling temporal dependencies in high-dimensional sequences: Application to polyphonic music generation and transcription,\u201d Proc. 29th International Conference on Machine Learning (ICML-12), ed. J.Langford and J. Pineau, New York, NY, USA, pp.1159-1166, ACM, 2012."},{"key":"33","unstructured":"[33] A.L. Maas, A.Y. Hannun, and A.Y. Ng, \u201cRectifier nonlinearities improve neural network acoustic models,\u201d Proc. 30th International Conference on Machine Learning (ICML-13)."},{"key":"34","unstructured":"[34] M. Bay, A.F. Ehmann, and J.S. Downie, \u201cEvaluation of multiple-f0 estimation and tracking systems,\u201d 2009 International Society for Music Information Retrieval Conference (ISMIR), pp.315-320, 2009."},{"key":"35","unstructured":"[35] D. Kingma and J. Ba, \u201cAdam: A method for stochastic optimization,\u201d arXiv preprint arXiv:1412.6980, 2014."},{"key":"36","doi-asserted-by":"crossref","unstructured":"[36] V. Panayotov, G. Chen, D. Povey, and S. Khudanpur, \u201cLibrispeech: an asr corpus based on public domain audio books,\u201d 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.5206-5210, IEEE, 2015. 10.1109\/icassp.2015.7178964","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"37","unstructured":"[37] 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 2011 Workshop on Automatic Speech Recognition and Understanding, IEEE Signal Processing Society, Dec. 2011. IEEE Catalog No.: CFP11SRW-USB."},{"key":"38","unstructured":"[38] D. Amodei, S. Ananthanarayanan, R. Anubhai, J. Bai, E.Battenberg, C. Case, J. Casper, B. Catanzaro, Q. Cheng, G. Chen, et al., \u201cDeep speech 2: End-to-end speech recognition in english and mandarin,\u201d International Conference on Machine Learning, pp.173-182, 2016."},{"key":"39","doi-asserted-by":"crossref","unstructured":"[39] A. Graves, S. Fern\u00e1ndez, F. Gomez, and J. Schmidhuber, \u201cConnectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks,\u201d Proc. 23rd international conference on Machine learning, pp.369-376, ACM, 2006. 10.1145\/1143844.1143891","DOI":"10.1145\/1143844.1143891"},{"key":"40","unstructured":"[40] A. Graves, \u201cPractical variational inference for neural networks,\u201d Advances in Neural Information Processing Systems, pp.2348-2356, 2011."},{"key":"41","doi-asserted-by":"crossref","unstructured":"[41] G.E. Hinton and D. Van Camp, \u201cKeeping the neural networks simple by minimizing the description length of the weights,\u201d Proc. sixth annual conference on Computational learning theory, pp.5-13, ACM, 1993. 10.1145\/168304.168306","DOI":"10.1145\/168304.168306"},{"key":"42","unstructured":"[42] Y. LeCun, J.S. Denker, and S.A. Solla, \u201cOptimal brain damage,\u201d Advances in neural information processing systems, pp.598-605, 1990."},{"key":"43","unstructured":"[43] S. Gupta, A. Agrawal, K. Gopalakrishnan, and P. Narayanan, \u201cDeep learning with limited numerical precision,\u201d Proc. 32nd International Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015, pp.1737-1746, 2015."},{"key":"44","unstructured":"[44] M. Courbariaux, J.P. David, and Y. Bengio, \u201cTraining deep neural networks with low precision multiplications,\u201d arXiv preprint arXiv:1412.7024, 2014."},{"key":"45","unstructured":"[45] M. Courbariaux, Y. Bengio, and J.P. David, \u201cBinaryConnect: Training deep neural networks with binary weights during propagations,\u201d Advances in Neural Information Processing Systems, pp.3123-3131, 2015."},{"key":"46","unstructured":"[46] S. Han, H. Mao, and W.J. Dally, \u201cDeep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding,\u201d arXiv preprint arXiv:1510.00149, 2015."},{"key":"47","unstructured":"[47] M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G.S. Corrado, A. Davis, J. Dean, M. Devin, S. Ghemawat, I.Goodfellow, A. Harp, G. Irving, M. Isard, Y. Jia, R. Jozefowicz, L. Kaiser, M. Kudlur, J. Levenberg, D. Man\u00e9, R. Monga, S. Moore, D. Murray, C. Olah, M. Schuster, J. Shlens, B. Steiner, I. Sutskever, K. Talwar, P. Tucker, V. Vanhoucke, V. Vasudevan, F. Vi\u00e9gas, O. Vinyals, P. Warden, M. Wattenberg, M. Wicke, Y. Yu, and X. Zheng, \u201cTensorFlow: Large-scale machine learning on heterogeneous systems,\u201d 2015. Software available from tensorflow.org."},{"key":"48","unstructured":"[48] Theano Development Team, \u201cTheano: A Python framework for fast computation of mathematical expressions,\u201d arXiv e-prints, vol.abs\/1605.02688, May 2016."},{"key":"49","doi-asserted-by":"crossref","unstructured":"[49] T.N. Sainath, B. Kingsbury, V. Sindhwani, E. Arisoy, and B.Ramabhadran, \u201cLow-rank matrix factorization for deep neural network training with high-dimensional output targets,\u201d 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp.6655-6659, IEEE, 2013. 10.1109\/icassp.2013.6638949","DOI":"10.1109\/ICASSP.2013.6638949"},{"key":"50","doi-asserted-by":"crossref","unstructured":"[50] Z. Lu, V. Sindhwani, and T.N. Sainath, \u201cLearning compact recurrent neural networks,\u201d 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.5960-5964, IEEE, 2016. 10.1109\/icassp.2016.7472821","DOI":"10.1109\/ICASSP.2016.7472821"},{"key":"51","unstructured":"[51] Y. Yang, D. Krompass, and V. Tresp, \u201cTensor-train recurrent neural networks for video classification,\u201d International Conference on Machine Learning, pp.3891-3900, 2017."},{"key":"52","doi-asserted-by":"crossref","unstructured":"[52] J. Ye, L. Wang, G. Li, D. Chen, S. Zhe, X. Chu, and Z. Xu, \u201cLearning compact recurrent neural networks with block-term tensor decomposition,\u201d Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp.9378-9387, 2018. 10.1109\/cvpr.2018.00977","DOI":"10.1109\/CVPR.2018.00977"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E103.D\/2\/E103.D_2019EDP7040\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,1,31]],"date-time":"2020-01-31T22:26:56Z","timestamp":1580509616000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E103.D\/2\/E103.D_2019EDP7040\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,1]]},"references-count":52,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2019edp7040","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2,1]]}}}