{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T14:38:02Z","timestamp":1740148682431,"version":"3.37.3"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2017,9,27]],"date-time":"2017-09-27T00:00:00Z","timestamp":1506470400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"the National key research and development program","award":["No2016YFB1001300"],"award-info":[{"award-number":["No2016YFB1001300"]}]},{"name":"the Fundamental Research Funds for the Central Universities","award":["WK2350000001"],"award-info":[{"award-number":["WK2350000001"]}]},{"name":"the CAS Strategic Priority Research Program","award":["XDB02070006"],"award-info":[{"award-number":["XDB02070006"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst"],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1007\/s11265-017-1288-9","type":"journal-article","created":{"date-parts":[[2017,9,27]],"date-time":"2017-09-27T06:14:30Z","timestamp":1506492870000},"page":"999-1011","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving the Decoding Efficiency of Deep Neural Network Acoustic Models by Cluster-Based Senone Selection"],"prefix":"10.1007","volume":"90","author":[{"given":"Jun-Hua","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7853-5273","authenticated-orcid":false,"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Si","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guo-Ping","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li-Rong","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,9,27]]},"reference":[{"issue":"2","key":"1288_CR1","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"LR Rabiner","year":"1989","unstructured":"Rabiner, L.R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), 257\u2013286.","journal-title":"Proceedings of the IEEE"},{"key":"1288_CR2","doi-asserted-by":"crossref","unstructured":"HHinton, G., Deng, L., Yu, D., Dahl, G.E., Mohamed, A.R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T.N., & Kingsbury, B. (2012). Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Processing Magazine, 29(6), 82\u201391.","DOI":"10.1109\/MSP.2012.2205597"},{"key":"1288_CR3","doi-asserted-by":"crossref","unstructured":"Yu, D., & Deng, L. (2015). Automatic Speech Recognition: A Deep Learning Approach. Springer Publishing Company, Incorporated.","DOI":"10.1007\/978-1-4471-5779-3"},{"issue":"1","key":"1288_CR4","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"GE Dahl","year":"2012","unstructured":"Dahl, G.E., Yu, D., Deng, L., & Acero, A. (2012). Context-dependent pre-training deep neural networks for large-vocabulary speech recognition. IEEE Transactions on Audio Speech, and Language Processing, 20(1), 30\u201342.","journal-title":"IEEE Transactions on Audio Speech, and Language Processing"},{"key":"1288_CR5","doi-asserted-by":"crossref","unstructured":"Sak, H., Senior, A., Rao, K., Irsoy, O., Graves, A., Beaufays, F., & Schalkwyk, J. (2015). Learning acoustic frame labeling for speech recognition with recurrent neural networks. In Proceedings of ICASSP (pp. 4280\u20134284). Brisbane, Australia.","DOI":"10.1109\/ICASSP.2015.7178778"},{"key":"1288_CR6","doi-asserted-by":"crossref","unstructured":"Sak, H., Senior, A., Rao, K., & Beaufays, F. (2015). Fast and accurate recurrent neural network acoustic models for speech recognition. In Proceedings of Interspeech (pp. 1468\u20131472). Dresden, Germany.","DOI":"10.21437\/Interspeech.2015-350"},{"key":"1288_CR7","doi-asserted-by":"crossref","unstructured":"Deng, L., Li, J., Ting Huang, J., Yao, K., Yu, D., Seide, F., Seltzer, M.L., Zweig, G., He, X., Williams, J., Gong, Y., & Acero, A. (2013). Recent advances in deep learning for speech research at microsoft. In Proceedings of ICASSP (pp. 8604\u20138609).","DOI":"10.1109\/ICASSP.2013.6639345"},{"key":"1288_CR8","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","volume":"61","author":"J Schmidhuber","year":"2015","unstructured":"Schmidhuber, J. (2015). Deep learning in neural networks: an overview. Neural Networks, 61, 85\u2013117.","journal-title":"Neural Networks"},{"key":"1288_CR9","unstructured":"Yu, D., Seide, F., Li, G., & Deng, L. (2012). Exploting sparseness in deep neural networks for large vocabulary speech recognition. In Proceedings of ICASSP (pp. 4409\u20134412)."},{"key":"1288_CR10","doi-asserted-by":"crossref","unstructured":"Lei, X., Senior, A., Gruenstein, A., & Sorensen, J. (2013). Accurate and compact large vocabulary speech recognition on mobile devices. In Proceedings of Interspeech (pp. 662\u2013665).","DOI":"10.21437\/Interspeech.2013-189"},{"key":"1288_CR11","doi-asserted-by":"crossref","unstructured":"Li, J., Zhao, R., Huang, J.T., & Gong, Y. (2014). Learning small-size DNN with output-distribution-based criteria. In Proceedings of Interspeech (pp. 1910\u20131914).","DOI":"10.21437\/Interspeech.2014-432"},{"key":"1288_CR12","doi-asserted-by":"crossref","unstructured":"Vanhoucke, V., Devin, M., & Heigold, G. (2013). Multiframe deep neural networks for acoustic modeling. In Proceedings of ICASSP.","DOI":"10.1109\/ICASSP.2013.6639137"},{"issue":"10","key":"1288_CR13","doi-asserted-by":"crossref","first-page":"2706","DOI":"10.4304\/jsw.9.10.2706-2712","volume":"9","author":"Y Xiao","year":"2014","unstructured":"Xiao, Y., Si, Y., Xu, J., Pan, J., & Yan, Y. (2014). Speeding up deep neural network based speech recognition systems. Journal of Software, 9(10), 2706\u20132712.","journal-title":"Journal of Software"},{"key":"1288_CR14","doi-asserted-by":"crossref","unstructured":"Sainath, T.N., Kingsbury, B., Sindhwani, V., Arisoy, E., & Ramabhadran, B. (2013). Low-rank matrix factorization for deep neural network training with high-dimensional output targets. In Proceeding of ICASSP (pp. 6655\u20136659).","DOI":"10.1109\/ICASSP.2013.6638949"},{"key":"1288_CR15","doi-asserted-by":"crossref","unstructured":"Xue, J., Li, J., & Gong, Y. (2013). Restructuring of deep neural network acoustic models with singular value decomposition. In Proceedings of Interspeech.","DOI":"10.21437\/Interspeech.2013-552"},{"key":"1288_CR16","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Yu, F.X., Feris, R.S., Kumar, S., Choudhary, A., & Chang, S.F. (2015). An exploration of parameter redundancy in deep networks with circulant projections. In Proceedings of the IEEE international conference on computer vision (pp. 2857\u20132865).","DOI":"10.1109\/ICCV.2015.327"},{"key":"1288_CR17","doi-asserted-by":"crossref","unstructured":"He, T., Fan, Y., Qian, Y., Tan, T., & Yu, K. (2014). Reshaping deep neural network for fast decoding by node-pruning. In Proceedings of ICASSP (pp. 245\u2013249).","DOI":"10.1109\/ICASSP.2014.6853595"},{"key":"1288_CR18","doi-asserted-by":"crossref","unstructured":"Tu, M., Berisha, V., Woolf, M., sun Seo, J., & Cao, Y. (2016). Ranking the parameters of deep neural network using the fisher information. In Proceedings of ICASSP.","DOI":"10.1109\/ICASSP.2016.7472157"},{"key":"1288_CR19","unstructured":"Vanhoucke, V., & Senior, A. (2011). Improving the speed of neural networkds on CPUs. In Deep learning and unsupervised feature learning workshop, NIPS 2011 (pp. 272\u2013281)."},{"issue":"4","key":"1288_CR20","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1109\/TASLP.2015.2392944","volume":"23","author":"P Zhou","year":"2015","unstructured":"Zhou, P., Jiang, H., Dai, L.R., Hu, Y., & Liu, Q.F. (2015). State-clustering based multiple deep neural networks modeling approach for speech recognition. IEEE\/ACM Transactions on Audio Speech and Language Processing, 23(4), 631\u2013642.","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"1288_CR21","doi-asserted-by":"crossref","unstructured":"Zhu, Y., & Mak, B. (2017). Speeding up softmax computations in dnn-based large vocabulary speech recognition by senone weight vector selection. In Proceedings of ICASSP (pp. 5335\u20135339).","DOI":"10.1109\/ICASSP.2017.7953175"},{"key":"1288_CR22","doi-asserted-by":"crossref","unstructured":"Chan, A., Sherwani, J., Mosur, R., & Rudnicky, A. (2004). Four-layer categorization scheme of fast GMM computation techniques in large vocabulary continuous speech recognition systems. In Proceedings of ICSLP.","DOI":"10.21437\/Interspeech.2004-272"},{"key":"1288_CR23","doi-asserted-by":"crossref","unstructured":"Lee, A., Kawahara, T., & Shikano, K. (2001). Gaussian mixture selection using context-independent HMM. In Proceedings of ICASSP, (Vol. 1 pp. 69\u201372). Salt Lake, UT.","DOI":"10.1109\/ICASSP.2001.940769"},{"key":"1288_CR24","doi-asserted-by":"crossref","unstructured":"Bocchieri, E. (1993). Vector quantization for the efficient computation of continuous density likelihoods. In Proceedings of ICASSP, (Vol. 2 pp. 692\u2013695). Minneapolis, MN, USA.","DOI":"10.1109\/ICASSP.1993.319405"},{"key":"1288_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, C., Zheng, R., & Xu, B. (2011). Data-driven Gaussian component selection for fast GMM-based speaker verification. In Proceedings of Interspeech (pp. 245\u2013248).","DOI":"10.21437\/Interspeech.2011-52"},{"key":"1288_CR26","unstructured":"Young, S., Evermann, G., Gales, M., Hain, T., Kershaw, D., Liu, X.A., Moore, G., Odell, J., Ollason, D., & Povey, D. (2006). The HTK book (for HTK version 3.4)."},{"issue":"1","key":"1288_CR27","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1109\/TASL.2011.2109382","volume":"20","author":"A Rahman Mohamed","year":"2012","unstructured":"Rahman Mohamed, A., Dahl, G.E., & Hinton, G. (2012). Acoustic modeling using deep belief networks. IEEE Transactions on Audio Speech, and Language Processing, 20(1), 14\u201322.","journal-title":"IEEE Transactions on Audio Speech, and Language Processing"},{"key":"1288_CR28","doi-asserted-by":"crossref","unstructured":"Mohri, M., Pereira, F., & Riley, M. (2008). Speech recognition with weighted finite-state transducers. In Springer handbook of speech processing (pp. 559\u2013584). Springer.","DOI":"10.1007\/978-3-540-49127-9_28"},{"key":"1288_CR29","volume-title":"On intelligence","author":"J Hawkins","year":"2007","unstructured":"Hawkins, J., & Blakeslee, S. (2007). On intelligence. New York: Times Books."},{"key":"1288_CR30","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1006\/dspr.1999.0361","volume":"10","author":"DA Reynolds","year":"2000","unstructured":"Reynolds, D.A., Quatieri, T.F., & Dunn, R.B. (2000). Speaker verification using adapted Gaussian mixture models. Digital Signal Processing, 10, 19\u201341.","journal-title":"Digital Signal Processing"},{"key":"1288_CR31","doi-asserted-by":"crossref","unstructured":"Karakos, D., Schwartz, R., Tsakalidis, S., & Le, Z. (2013). Score normalization and system combination for improved keyword spotting. In Automatic speech recognition and understanding (pp. 210\u2013215).","DOI":"10.1109\/ASRU.2013.6707731"},{"key":"1288_CR32","doi-asserted-by":"crossref","unstructured":"Chiu, J., Wang, Y., Trmal, J., Povey, D., Chen, G., & Rudnicky, A.I. (2014). Combination of fst and cn search in spoken term detection. In Proceedings of Interspeech (p. 2784).","DOI":"10.21437\/Interspeech.2014-532"},{"key":"1288_CR33","doi-asserted-by":"crossref","unstructured":"Godfrey, J.J., Holliman, E.C., & Mcdaniel, J. (1992). Switchboard: telephone speech corpus for research and development. In IEEE international conference on acoustics, speech and signal processing, (Vol.1 pp. 517\u2013520).","DOI":"10.1109\/ICASSP.1992.225858"},{"issue":"1","key":"1288_CR34","first-page":"37","volume":"2","author":"DM Powers","year":"2011","unstructured":"Powers, D.M. (2011). Evaluation: from precision, recall and f-meansure to roc, informedness, markedeness & correlation. Journal of Machine Learning Technologies, 2(1), 37\u201363.","journal-title":"Journal of Machine Learning Technologies"},{"key":"1288_CR35","unstructured":"David, C.C., Miller, D., & Walker, K. (2004). The fisher corpus: a resource for the next generations of speech-to. In International conference on language resources & evaluation (pp. 69\u201371)."}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-017-1288-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-017-1288-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-017-1288-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T14:14:08Z","timestamp":1659536048000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-017-1288-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9,27]]},"references-count":35,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2018,7]]}},"alternative-id":["1288"],"URL":"https:\/\/doi.org\/10.1007\/s11265-017-1288-9","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"type":"print","value":"1939-8018"},{"type":"electronic","value":"1939-8115"}],"subject":[],"published":{"date-parts":[[2017,9,27]]}}}