{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:51:53Z","timestamp":1740099113982,"version":"3.37.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319995786"},{"type":"electronic","value":"9783319995793"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-99579-3_4","type":"book-chapter","created":{"date-parts":[[2018,8,24]],"date-time":"2018-08-24T07:36:09Z","timestamp":1535096169000},"page":"32-41","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Exploring End-to-End Techniques for Low-Resource Speech Recognition"],"prefix":"10.1007","author":[{"given":"Vladimir","family":"Bataev","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maxim","family":"Korenevsky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ivan","family":"Medennikov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Zatvornitskiy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,8,25]]},"reference":[{"key":"4_CR1","unstructured":"CTC Decoder for PyTorch. https:\/\/github.com\/parlance\/ctcdecode"},{"key":"4_CR2","unstructured":"Kaldi Recipe Results for Turkish Language. https:\/\/github.com\/kaldi-asr\/kaldi\/blob\/master\/egs\/babel\/s5d\/results\/results.105-turkish-fullLP.official.conf.jtrmal1%40jhu.edu.2015-11-28T144317-0500"},{"key":"4_CR3","unstructured":"Sclite Scoring Package. http:\/\/www1.icsi.berkeley.edu\/Speech\/docs\/sctk-1.2\/sclite.htm"},{"key":"4_CR4","unstructured":"The SRI Language Modeling Toolkit. http:\/\/www.speech.sri.com\/projects\/srilm\/"},{"key":"4_CR5","unstructured":"Turkish Alphabet. https:\/\/en.wikipedia.org\/wiki\/Turkish_alphabet"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Alum\u00e4e, T., et al.: The 2016 BBN Georgian telephone speech keyword spotting system. In: Proceedings of ICASSP, pp. 5755\u20135759 (2017)","DOI":"10.1109\/ICASSP.2017.7953259"},{"key":"4_CR7","unstructured":"Amodei, D., et al.: Deep speech 2: end-to-end speech recognition in English and Mandarin (2015). arxiv:1512.02595"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Chan, W., Jaitly, N., Le, Q.V., Vinyals, O.: Listen, attend and spell: a neural network for large vocabulary conversational speech recognition. In: Proceedings of ICASSP, pp. 4960\u20134964 (2016)","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"4_CR9","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1007\/978-3-319-11581-8_54","volume-title":"Speech and Computer, Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","author":"G Chernykh","year":"2014","unstructured":"Chernykh, G., Korenevsky, M., Levin, K., Ponomareva, I., Tomashenko, N.: State level control for acoustic model training. In: Ronzhin, A., Potapova, R., Delic, V. (eds.) SPECOM 2014. LNCS (LNAI), vol. 8773, pp. 435\u2013442. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-11581-8_54"},{"key":"4_CR10","unstructured":"Collobert, R., Puhrsch, C., Synnaeve, G.: Wav2letter: an end-to-end ConvNet-based speech recognition system (2016). arxiv:1609.03193"},{"key":"4_CR11","unstructured":"Dalmia, S., Sanabria, R., Metze, F., Black, A.W.: Sequence-based multi-lingual low resource speech recognition (2018). arxiv:1802.07420"},{"key":"4_CR12","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-66429-3_1","volume-title":"Speech and Computer","author":"MJF Gales","year":"2017","unstructured":"Gales, M.J.F., Knill, K.M., Ragni, A.: Low-resource speech recognition and keyword-spotting. In: Karpov, A., Potapova, R., Mporas, I. (eds.) SPECOM 2017. LNCS (LNAI), vol. 10458, pp. 3\u201319. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-66429-3_1"},{"key":"4_CR13","unstructured":"Graves, A.: Sequence transduction with recurrent neural networks (2012). arxiv:1211.3711"},{"key":"4_CR14","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: Proceedings of ICML, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"4_CR15","unstructured":"Hannun, A.Y., et al.: Deep speech: scaling up end-to-end speech recognition (2014). arxiv:1412.5567"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Khokhlov, Y.Y., et al.: The STC keyword search system for OpenKWS 2016 evaluation. In: Proceedings of INTERSPEECH, pp. 3602\u20133606 (2017)","DOI":"10.21437\/Interspeech.2017-1212"},{"key":"4_CR17","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/978-3-319-23132-7_3","volume-title":"Speech and Computer","author":"O Khomitsevich","year":"2015","unstructured":"Khomitsevich, O., Mendelev, V., Tomashenko, N., Rybin, S., Medennikov, I., Kudubayeva, S.: A bilingual Kazakh-Russian system for automatic speech recognition and synthesis. In: Ronzhin, A., Potapova, R., Fakotakis, N. (eds.) SPECOM 2015. LNCS (LNAI), vol. 9319, pp. 25\u201333. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-23132-7_3"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Kingsbury, B.: Lattice-based optimization of sequence classification criteria for neural-network acoustic modeling. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2009, pp. 3761\u20133764 (2009)","DOI":"10.1109\/ICASSP.2009.4960445"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Ko, T., Peddinti, V., Povey, D., Khudanpur, S.: Audio augmentation for speech recognition. In: Proceedings of INTERSPEECH (2015)","DOI":"10.21437\/Interspeech.2015-711"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Levin, K., et al.: Automated closed captioning for Russian live broadcasting. In: Proceedings of INTERSPEECH, pp. 1438\u20131442 (2014)","DOI":"10.21437\/Interspeech.2014-352"},{"key":"4_CR21","unstructured":"Liptchinsky, V., Synnaeve, G., Collobert, R.: Letter-based speech recognition with Gated ConvNets (2017). arxiv:1712.09444"},{"key":"4_CR22","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: Proceedings of ASRU, pp. 167\u2013174 (2015)","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"4_CR23","unstructured":"Povey, D., et al.: The Kaldi speech recognition toolkit. In: Proceedings of ASRU (2011)"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Neurocomputing: foundations of research. In: Learning Representations by Back-Propagating Errors, pp. 696\u2013699. MIT Press, Cambridge (1988)","DOI":"10.7551\/mitpress\/4943.003.0042"},{"key":"4_CR25","unstructured":"Zhou, Y., Xiong, C., Socher, R.: Improved regularization techniques for end-to-end speech recognition (2017). arxiv:1712.07108"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-99579-3_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T15:20:44Z","timestamp":1720538444000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-99579-3_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319995786","9783319995793"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-99579-3_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}