{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T12:10:02Z","timestamp":1748607002099,"version":"3.41.0"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319231310"},{"type":"electronic","value":"9783319231327"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-23132-7_23","type":"book-chapter","created":{"date-parts":[[2015,9,3]],"date-time":"2015-09-03T07:41:18Z","timestamp":1441266078000},"page":"186-192","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Deep Neural Network Based Continuous Speech Recognition for Serbian Using the Kaldi Toolkit"],"prefix":"10.1007","author":[{"given":"Branislav","family":"Popovi\u0107","sequence":"first","affiliation":[]},{"given":"Stevan","family":"Ostrogonac","sequence":"additional","affiliation":[]},{"given":"Edvin","family":"Pakoci","sequence":"additional","affiliation":[]},{"given":"Nik\u0161a","family":"Jakovljevi\u0107","sequence":"additional","affiliation":[]},{"given":"Vlado","family":"Deli\u0107","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,9,4]]},"reference":[{"key":"23_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/978-3-319-01931-4_42","volume-title":"Speech and Computer","author":"V Deli\u0107","year":"2013","unstructured":"Deli\u0107, V., Se\u010dujski, M., Jakovljevi\u0107, N., Pekar, D., Mi\u0161kovi\u0107, D., Popovi\u0107, B., Ostrogonac, S., Bojani\u0107, M., Kne\u017eevi\u0107, D.: Speech and language resources within speech recognition and synthesis systems for Serbian and kindred south slavic languages. In: \u017delezn\u00fd, M., Habernal, I., Ronzhin, A. (eds.) SPECOM 2013. LNCS, vol. 8113, pp. 319\u2013326. Springer, Heidelberg (2013)"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Young, S.J., Odell, J., Woodland, P.C.: Tree-based state tying for high accuracy acoustic modelling. In: ARPA Human Language Technology Workshop, pp. 307\u2013312, Princeton (1994)","DOI":"10.3115\/1075812.1075885"},{"key":"23_CR3","unstructured":"Jakovljevi\u0107, N., Mi\u0161kovi\u0107, D., Janev, M., Pekar, D.: A decoder for large vocabulary speech recognition. In: 18th International Conference on Systems, Signals and Image Processing, IWSSIP, pp. 1\u20134, Sarajevo (2011)"},{"key":"23_CR4","unstructured":"Povey, D., et al.: The Kaldi speech recognition toolkit. In: IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU, pp. 1\u20134, Waikoloa (2011)"},{"key":"23_CR5","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1006\/csla.2001.0184","volume":"16","author":"M Mohri","year":"2002","unstructured":"Mohri, M., Pereira, F., Riley, M.: Weighted finite-state transducers in speech recognition. Comput. Speech Lang. 16, 69\u201388 (2002)","journal-title":"Comput. Speech Lang."},{"issue":"2","key":"23_CR6","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1145\/567806.567807","volume":"28","author":"LS Blackford","year":"2002","unstructured":"Blackford, L.S., et al.: An updated set of basic linear algebra subprograms (BLAS). ACM Trans. Math. Softw. 28(2), 135\u2013151 (2002)","journal-title":"ACM Trans. Math. Softw."},{"key":"23_CR7","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719604","volume-title":"LAPACK Users\u2019 Guide","author":"E Anderson","year":"1999","unstructured":"Anderson, E., et al.: LAPACK Users\u2019 Guide. Society for Industrial and Applied Mathematics (SIAM), Philadelphia (1999)"},{"key":"23_CR8","unstructured":"Popovi\u0107, B., Pakoci, E., Ostrogonac, S., Pekar, D.: Large vocabulary continuous speech recognition for Serbian using the Kaldi toolkit. In: 10th Digital Speech and Image Processing, DOGS, pp. 31\u201334, Novi Sad (2014)"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Vesel\u00fd, K., Arnab, G., Luk\u00e1\u0161, B., Povey, D.: Sequence-discriminative training of deep neural networks. In: International Speech Communication Association, Interspeech 2013, pp. 2345\u20132349, Lyon (2013)","DOI":"10.21437\/Interspeech.2013-548"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Povey, D., Kanevsky, D., Kingsbury, B., Ramabhadran, B., Saon, G., Visweswariah, K.: Boosted MMI for model and feature-space discriminative training. In: 33rd International Conference on Acoustics, Speech and Signal Processing, ICASSP, pp. 4057\u20134060, Las Vegas (2008)","DOI":"10.1109\/ICASSP.2008.4518545"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Povey D., Woodland, P.C.: Minimum phone error and i-smoothing for improved discriminative training. In: 27th International Conference on Acoustics, Speech and Signal Processing, ICASSP, pp. I-105\u2013I-108, Orlando (2002)","DOI":"10.1109\/ICASSP.2002.1005687"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Povey, D., Kuo, H-K.J., Soltau, H.: Fast speaker adaptive training for speech recognition. In: 9th Annual Conference of the International Speech Communication Association, INTERSPEECH, pp. 1245\u20131248, Brisbane (2008)","DOI":"10.21437\/Interspeech.2008-377"},{"key":"23_CR13","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1016\/j.csl.2010.06.003","volume":"25","author":"D Povey","year":"2011","unstructured":"Povey, D., et al.: The subspace Gaussian mixture model - a structured model for speech recognition. Comput. Speech Lang. 25, 404\u2013439 (2011)","journal-title":"Comput. Speech Lang."},{"key":"23_CR14","unstructured":"Carreira-Perpi\u00f1\u00e1n, M., Hinton, G.: On contrastive divergence learning. In: 10th International Workshop on Artifitial Intelligence and Statistic, AISTATS, pp. 59\u201366, Barbados (2005)"},{"key":"23_CR15","unstructured":"Stolcke, A., Zheng, J., Wang, W., Abrash, V.: SRILM at sixteen: update and outlook. In: IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU, Waikoloa (2011)"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Kneser, R., Ney, H.: Improved backing-off for M-gram language modeling. In: 20th International Conference on Acoustics, Speech and Signal Processing, ICASSP, pp. 181\u2013184, Detroit (1995)","DOI":"10.1109\/ICASSP.1995.479394"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-23132-7_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T11:36:49Z","timestamp":1748605009000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-23132-7_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319231310","9783319231327"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-23132-7_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"4 September 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}