{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T06:27:44Z","timestamp":1725863264651},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319439570"},{"type":"electronic","value":"9783319439587"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-43958-7_13","type":"book-chapter","created":{"date-parts":[[2016,8,12]],"date-time":"2016-08-12T02:11:41Z","timestamp":1470967901000},"page":"116-123","source":"Crossref","is-referenced-by-count":6,"title":["Advances in STC Russian Spontaneous Speech Recognition System"],"prefix":"10.1007","author":[{"given":"Ivan","family":"Medennikov","sequence":"first","affiliation":[]},{"given":"Alexey","family":"Prudnikov","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,8,13]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Vesely, K., Ghoshal, A., Burget, L., Povey, D.: Sequence-discriminative training of deep neural networks. In: 14th Annual Conference of the International Speech Communication Association (Interspeech), pp. 2345\u20132349. Lyon (2013)","DOI":"10.1109\/ASRU.2013.6707741"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Saon, G., Soltau, H., Nahamoo, D., Picheny, M.: Speaker adaptation of neural network acoustic models using i-vectors. In: IEEE workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 55\u201359. Olomouc (2013)","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Soltau, H., Saon, G., Sainath, T.N.: Joint training of convolutional and non-convolutional neural networks. In: 39th International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5572\u20135576. Florence (2014)","DOI":"10.1109\/ICASSP.2014.6854669"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Saon, G., Kuo, H.-K., Rennie, S., Picheny, M.: The IBM 2015 english conversational telephone speech recognition system. In: 16th Annual Conference of the International Speech Communication Association (Interspeech). Dresden (2015)","DOI":"10.21437\/Interspeech.2016-1460"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Mohamed, A., Seide, F., Yu, D., Droppo, J., Stolcke, A., Zweig, G., Penn, G.: Deep bi-directional recurrent networks over spectral windows. In: IEEE workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 55\u201359. Scottsdale (2015)","DOI":"10.1109\/ASRU.2015.7404777"},{"issue":"6","key":"13_CR6","doi-asserted-by":"publisher","first-page":"957","DOI":"10.17586\/2226-1494-2015-15-6-957-968","volume":"15","author":"IB Tampel","year":"2015","unstructured":"Tampel, I.B.: Automatic speech recognition -the main stages over last 50 years. Sci. Tech. J. Inf. Technol. Mech. Opt. 15(6), 957\u2013968 (2015). doi: 10.17586\/2226-1494-2015-15-6-957-968","journal-title":"Sci. Tech. J. Inf. Technol. Mech. Opt."},{"key":"13_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1007\/978-3-319-23132-7_29","volume-title":"Speech and Computer","author":"A Prudnikov","year":"2015","unstructured":"Prudnikov, A., Medennikov, I., Mendelev, V., Korenevsky, M., Khokhlov, Y.: Improving acoustic models for russian spontaneous speech recognition. In: Ronzhin, A., Potapova, R., Fakotakis, N. (eds.) SPECOM 2015. LNCS, vol. 9319, pp. 234\u2013242. Springer, Heidelberg (2015)"},{"key":"13_CR8","unstructured":"Povey, D., et al.: The kaldi speech recognition toolkit. In: IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 1\u20134. Big Island (2011)"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Stolcke, A.: SRILM \u2013 an extensible language modeling toolkit. In: Seventh International Conference on Spoken Language Processing, vol. 3, pp. 901\u2013904 (2002)","DOI":"10.21437\/ICSLP.2002-303"},{"issue":"1","key":"13_CR10","doi-asserted-by":"publisher","first-page":"195","DOI":"10.17586\/2226-1494-2016-16-1-195-197","volume":"16","author":"IP Medennikov","year":"2016","unstructured":"Medennikov, I.P.: Speaker-dependent features for spontaneous speech recognition. Sci. Tech. J. Inf. Technol. Mech. Opt. 16(1), 195\u2013197 (2016). doi: 10.17586\/2226-1494-2016-16-1-195-197","journal-title":"Sci. Tech. J. Inf. Technol. Mech. Opt."},{"key":"13_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1007\/978-3-319-01931-4_37","volume-title":"Speech and Computer","author":"A Kozlov","year":"2013","unstructured":"Kozlov, A., Kudashev, O., Matveev, Y., Pekhovsky, T., Simonchik, K., Shulipa, A.: SVID speaker recognition system for NIST SRE 2012. In: \u017delezn\u00fd, M., Habernal, I., Ronzhin, A. (eds.) SPECOM 2013. LNCS, vol. 8113, pp. 278\u2013285. Springer, Heidelberg (2013)"},{"issue":"2","key":"13_CR12","doi-asserted-by":"publisher","first-page":"379","DOI":"10.17586\/2226-1494-2016-16-2-379-381","volume":"16","author":"IP Medennikov","year":"2016","unstructured":"Medennikov, I.P.: Two-step algorithm of training initialization for acoustic models based on deep neural networks. Sci. Tech. J. Inf. Technol. Mech. Opt. 16(2), 379\u2013381 (2016). doi: 10.17586\/2226-1494-2016-16-2-379-381","journal-title":"Sci. Tech. J. Inf. Technol. Mech. Opt."},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Sak, H., Senior, A., Beaufays, F.: Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In: 15th Annual Conference of the International Speech Communication Association (Interspeech). Singapore (2014)","DOI":"10.21437\/Interspeech.2014-80"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Karafiat, M., Burget, L., Cernocky, J., Khudanpur, S.: Recurrent neural network based language model. In: 11th Annual Conference of the International Speech Communication Association (Interspeech), pp. 1045\u20131048. Makuhari (2010)","DOI":"10.21437\/Interspeech.2010-343"},{"key":"13_CR15","unstructured":"Zaremba, W., Sutskever, I., Vinyals, O.: Recurrent neural network regularization. arXiv preprint (2014). arXiv:1409.2329"},{"key":"13_CR16","unstructured":"Abadi, M., et al.: TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems (2015). http:\/\/tensorflow.org\/"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Ko, T., Peddinti, V., Povey, D., Khudanpur, S.: Audio augmentation for speech recognition. In: 16th Annual Conference of the International Speech Communication Association (Interspeech). Dresden (2015)","DOI":"10.21437\/Interspeech.2015-711"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-43958-7_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,19]],"date-time":"2023-08-19T16:57:57Z","timestamp":1692464277000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-43958-7_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319439570","9783319439587"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-43958-7_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}