{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T12:16:03Z","timestamp":1770898563517,"version":"3.50.1"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030420574","type":"print"},{"value":"9783030420581","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","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":[[2020]]},"DOI":"10.1007\/978-3-030-42058-1_33","type":"book-chapter","created":{"date-parts":[[2020,3,3]],"date-time":"2020-03-03T12:03:51Z","timestamp":1583237031000},"page":"391-401","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["End-to-End Speech Recognition in Agglutinative Languages"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8318-3794","authenticated-orcid":false,"given":"Orken","family":"Mamyrbayev","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0766-2229","authenticated-orcid":false,"given":"Keylan","family":"Alimhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bagashar","family":"Zhumazhanov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7720-7945","authenticated-orcid":false,"given":"Tolganay","family":"Turdalykyzy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4919-4419","authenticated-orcid":false,"given":"Farida","family":"Gusmanova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,3,4]]},"reference":[{"key":"33_CR1","doi-asserted-by":"publisher","first-page":"1062","DOI":"10.1289\/ehp.7908","volume":"113","author":"FP Perera","year":"2005","unstructured":"Perera, F.P., et al.: Relationship between polycyclic aromatic hydrocarbon\u2013DNA adducts and proximity to the World Trade Center and effects on fetal growth. Environ. Health Perspect. 113, 1062\u20131067 (2005)","journal-title":"Environ. Health Perspect."},{"key":"33_CR2","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1007\/978-3-030-14802-7_40","volume-title":"Intelligent Information and Database Systems","author":"O Mamyrbayev","year":"2019","unstructured":"Mamyrbayev, O., Turdalyuly, M., Mekebayev, N., Alimhan, K., Kydyrbekova, A., Turdalykyzy, T.: Automatic recognition of Kazakh speech using deep neural networks. In: Nguyen, N.T., Gaol, F.L., Hong, T.-P., Trawi\u0144ski, B. (eds.) ACIIDS 2019. LNCS (LNAI), vol. 11432, pp. 465\u2013474. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-14802-7_40"},{"key":"33_CR3","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.21437\/Interspeech.2010-343","volume":"2","author":"T Mikolov","year":"2010","unstructured":"Mikolov, T., et al.: Recurrent neural network based language model. Interspeech 2, 1045\u20131048 (2010)","journal-title":"Interspeech"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Rao, K., Peng, F., Sak, H., Beaufays, F.: Grapheme-to-phoneme conversion using long short-term memory recurrent neural networks. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4225\u20134229 (2015)","DOI":"10.1109\/ICASSP.2015.7178767"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Jaitly, N., Hinton, G.: Learning a better representation of speech soundwaves using restricted boltzmann machines. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5884\u20135887 (2011)","DOI":"10.1109\/ICASSP.2011.5947700"},{"key":"33_CR6","unstructured":"Smolensky, P.: Information processing in dynamical systems: foundations of harmony theory. Colorado University at Boulder Department of Computer Science, pp. 194\u2013281 (1986)"},{"key":"33_CR7","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1007\/978-3-319-68456-7_17","volume-title":"Statistical Language and Speech Processing","author":"J Van\u011bk","year":"2017","unstructured":"Van\u011bk, J., Zelinka, J., Soutner, D., Psutka, J.: A regularization post layer: an additional way how to make deep neural networks robust. In: Camelin, N., Est\u00e8ve, Y., Mart\u00edn-Vide, C. (eds.) SLSP 2017. LNCS (LNAI), vol. 10583, pp. 204\u2013214. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-68456-7_17"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Kim, S., Hori, T., Watanabe, S.: Joint CTC-attention based end-to-end speech recognition using multi-task learning. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2017)","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"33_CR9","unstructured":"Aida-Zade, K., Rustamov, S., Mustafayev, E.: Principles of construction of speech recognition system by the example of Azerbaijan language.\u00a0In: International Symposium on Innovations in Intelligent Systems and Applications, pp. 378\u2013382 (2009)"},{"key":"33_CR10","unstructured":"Hannun, A., et al.: DeepSpeech: scaling up end-to-end speech recognition, arXiv:1412.5567 (2014)"},{"key":"33_CR11","unstructured":"Zhang, Z., et al.: Deep recurrent convolutional neural network: improving performance for speech recognition (2016). preprint: arXiv:1611.07174 . https:\/\/arxiv.org\/abs\/1611.07174"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"Bahdanau, D., et al.: End-to-end attention-based large vocabulary speech recognition. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4945\u20134949. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"33_CR13","unstructured":"Zhang, Y., et al.: Towards end-to-end speech recognition with deep convolutional neural networks (2017). preprint: arXiv:1701.02720 . https:\/\/arxiv.org\/abs\/1701.02720"},{"key":"33_CR14","unstructured":"Povey, D., et al.: The Kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding, 4 p. IEEE Signal Processing Society (2011)"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Soltau, H., Liao, H., Sak, H.: Neural speech recognizer: acoustic-to-word LSTM model for large vocabulary speech recognition. arXiv:1610.09975 (2016)","DOI":"10.21437\/Interspeech.2017-1566"},{"key":"33_CR16","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 the 23rd International Conference on Machine Learning, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"33_CR17","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1007\/978-3-319-66429-3_33","volume-title":"Speech and Computer","author":"B Popovi\u0107","year":"2017","unstructured":"Popovi\u0107, B., Pakoci, E., Pekar, D.: End-to-End large vocabulary speech recognition for the Serbian language. In: Karpov, A., Potapova, R., Mporas, I. (eds.) SPECOM 2017. LNCS (LNAI), vol. 10458, pp. 343\u2013352. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-66429-3_33"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Boulanger-Lewandowski, N., Bengio, Y., Vincent, P.: High-dimensional sequence transduction. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3178\u20133182 (2013)","DOI":"10.1109\/ICASSP.2013.6638244"},{"key":"33_CR19","unstructured":"Wang, Y., Deng, X., Pu, S., Huang, Z.: Residual convolutional CTC networks for automatic speech recognition (2017). preprint: arXiv:1702.07793 . https:\/\/arxiv.org\/abs\/1702.07793"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Rustamov, S., Gasimov, E., Hasanov, R., Jahangirli, S., Mustafayev, E., Usikov, D.: Speech recognition in flight simulator. In: Aegean International Textile and Advanced Engineering Conference. IOP Conference Series: Materials Science and Engineering, vol. 459 (2018)","DOI":"10.1088\/1757-899X\/459\/1\/012005"},{"key":"33_CR21","unstructured":"Gulmira, T., Alymzhan, T., Orken, M., Rustam, M.: Neural named entity recognition for Kazakh. In: 20th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing), 7\u201313 April 2019, La Rochelle, France. Lecture Notes in Computer Science (2019)"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Toleu, A., Tolegen, G., Makazhanov, A.: Character-aware neural morphological disambiguation. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 666\u2013671. Association for Computational Linguistics, Vancouver (2017)","DOI":"10.18653\/v1\/P17-2105"}],"container-title":["Lecture Notes in Computer Science","Intelligent Information and Database Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-42058-1_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T09:51:13Z","timestamp":1666000273000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-42058-1_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030420574","9783030420581"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-42058-1_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"4 March 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACIIDS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Intelligent Information and Database Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Phuket","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 March 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 March 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aciids2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aciids.pwr.edu.pl\/2020\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}