{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:48:46Z","timestamp":1740098926861,"version":"3.37.3"},"publisher-location":"Cham","reference-count":12,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319664286"},{"type":"electronic","value":"9783319664293"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"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":[[2017]]},"DOI":"10.1007\/978-3-319-66429-3_33","type":"book-chapter","created":{"date-parts":[[2017,8,12]],"date-time":"2017-08-12T02:02:55Z","timestamp":1502503375000},"page":"343-352","source":"Crossref","is-referenced-by-count":5,"title":["End-to-End Large Vocabulary Speech Recognition for the Serbian Language"],"prefix":"10.1007","author":[{"given":"Branislav","family":"Popovi\u0107","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edvin","family":"Pakoci","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Darko","family":"Pekar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,8,13]]},"reference":[{"key":"33_CR1","unstructured":"Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motl\u00ed\u010dek, P., Qian, Y., Schwarz, P., Silovsk\u00fd, J., Stemmer, G., Vesel\u00fd, K.: The Kaldi speech recognition toolkit. In: IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 1\u20134. IEEE Signal Processing Society (2011)"},{"key":"33_CR2","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, Serbia (2014)"},{"key":"33_CR3","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, Las Vegas, pp. 4057\u20134060 (2008)","DOI":"10.1109\/ICASSP.2008.4518545"},{"key":"33_CR4","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, Orlando, pp. I-105\u2013I-108 (2002)","DOI":"10.1109\/ICASSP.2002.5743665"},{"key":"33_CR5","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, Brisbane, pp. 1245\u20131248 (2008)","DOI":"10.21437\/Interspeech.2008-377"},{"key":"33_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1007\/978-3-319-43958-7_7","volume-title":"Speech and Computer","author":"E Pakoci","year":"2016","unstructured":"Pakoci, E., Popovi\u0107, B., Jakovljevi\u0107, N., Pekar, D., Yassa, F.: A phonetic segmentation procedure based on hidden markov models. In: Ronzhin, A., Potapova, R., N\u00e9meth, G. (eds.) SPECOM 2016. LNCS, vol. 9811, pp. 67\u201374. Springer, Cham (2016). doi: 10.1007\/978-3-319-43958-7_7"},{"key":"33_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1007\/978-3-319-23132-7_23","volume-title":"Speech and Computer","author":"B Popovi\u0107","year":"2015","unstructured":"Popovi\u0107, B., Ostrogonac, S., Pakoci, E., Jakovljevi\u0107, N., Deli\u0107, V.: Deep neural network based continuous speech recognition for serbian using the Kaldi toolkit. In: Ronzhin, A., Potapova, R., Fakotakis, N. (eds.) SPECOM 2015. LNCS, vol. 9319, pp. 186\u2013192. Springer, Cham (2015). doi: 10.1007\/978-3-319-23132-7_23"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Miao, Y., Gowayyed, M., Metze, F.: EESEN: End-to-end speech recognition using deep RNN models and WFST-based decoding. In: Automatic Speech Recognition and Understanding Workshop, ASRU 2015, arXiv:1507.08240 (2015)","DOI":"10.1109\/ASRU.2015.7404790"},{"issue":"1","key":"33_CR9","doi-asserted-by":"crossref","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(1), 69\u201388 (2002)","journal-title":"Comput. Speech Lang."},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: 23rd International Conference on Machine Learning, pp. 369\u2013376. ACM (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"33_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/978-3-540-76336-9_3","volume-title":"Implementation and Application of Automata","author":"C Allauzen","year":"2007","unstructured":"Allauzen, C., Riley, M., Schalkwyk, J., Skut, W., Mohri, M.: OpenFst: a general and efficient weighted finite-state transducer library. In: Holub, J., \u017d\u010f\u00e1rek, J. (eds.) CIAA 2007. LNCS, vol. 4783, pp. 11\u201323. Springer, Heidelberg (2007). doi: 10.1007\/978-3-540-76336-9_3"},{"key":"33_CR12","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, Detroit, pp. 181\u2013184 (1995)","DOI":"10.1109\/ICASSP.1995.479394"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-66429-3_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T03:34:21Z","timestamp":1659324861000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-66429-3_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319664286","9783319664293"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-66429-3_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}