{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T23:57:33Z","timestamp":1743119853315,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031417733"},{"type":"electronic","value":"9783031417740"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-41774-0_33","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T03:25:20Z","timestamp":1695266720000},"page":"419-429","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Difficulties Developing a Children\u2019s Speech Recognition System for Language with Limited Training Data"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4975-6493","authenticated-orcid":false,"given":"Dina","family":"Oralbekova","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8318-3794","authenticated-orcid":false,"given":"Orken","family":"Mamyrbayev","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5124-5759","authenticated-orcid":false,"given":"Mohamed","family":"Othman","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0766-2229","authenticated-orcid":false,"given":"Keylan","family":"Alimhan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9826-0286","authenticated-orcid":false,"family":"NinaKhairova","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3641-8260","authenticated-orcid":false,"given":"Aliya","family":"Zhunussova","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"issue":"3","key":"33_CR1","doi-asserted-by":"publisher","first-page":"251","DOI":"10.2307\/1268779","volume":"33","author":"BH Juang","year":"1991","unstructured":"Juang, B.H., Rabiner, L.R.: Hidden markov models for speech recognition. Technometrics 33(3), 251 (1991). https:\/\/doi.org\/10.2307\/1268779","journal-title":"Technometrics"},{"issue":"6","key":"33_CR2","doi-asserted-by":"publisher","first-page":"EL221","DOI":"10.1121\/1.3124659","volume":"125","author":"JC Brown","year":"2009","unstructured":"Brown, J.C., Smaragdis, P.: Hidden Markov and Gaussian mixture models for automatic call classification. J. Acoustical Soc. Am. 125(6), EL221\u2013EL224 (2009). https:\/\/doi.org\/10.1121\/1.3124659","journal-title":"J. Acoustical Soc. Am."},{"issue":"6","key":"33_CR3","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., et al.: Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Process. Magazine 29(6), 82\u201397 (2012)","journal-title":"IEEE Signal Process. Magazine"},{"issue":"4","key":"33_CR4","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1007\/s10772-017-9461-x","volume":"20","author":"S Ghaffarzadegan","year":"2017","unstructured":"Ghaffarzadegan, S., Bo\u0159il, H., Hansen, J.H.L.: Deep neural network training for whispered speech recognition using small databases and generative model sampling. Int. J. Speech Technol. 20(4), 1063\u20131075 (2017). https:\/\/doi.org\/10.1007\/s10772-017-9461-x","journal-title":"Int. J. Speech Technol."},{"key":"33_CR5","unstructured":"Children\u2019s Art School No. 4, Engels Homepage. https:\/\/engels-dshi4.ru\/index.php?option=com_content&view=article&id=86:tormanova-o-v-detskij-golos-i-osobennosti-ego-razvitiya&catid=18&Itemid=131. Last accessed 16 Mar 2023"},{"key":"33_CR6","unstructured":"https:\/\/te-st.org\/2021\/06\/02\/voice-assistants-and-problems\/"},{"key":"33_CR7","doi-asserted-by":"publisher","first-page":"8337","DOI":"10.1038\/s41598-022-12260-y","volume":"12","author":"O Mamyrbayev","year":"2022","unstructured":"Mamyrbayev, O., Oralbekova, D., Alimhan, K., Othman, M., Turdalykyzy, T.: A study of transformer-based end-to-end speech recognition system for Kazakh language. Sci. Rep. 12, 8337 (2022). https:\/\/doi.org\/10.1038\/s41598-022-12260-y","journal-title":"Sci. Rep."},{"issue":"2","key":"33_CR8","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s10772-022-09983-8","volume":"26","author":"OZ Mamyrbayev","year":"2022","unstructured":"Mamyrbayev, O.Z., Oralbekova, D.O., Alimhan, K., Nuranbayeva, B.M.: Hybrid end-to-end model for Kazakh speech recognition. Int. J. Speech Technol. 26(2), 261\u2013270 (2022). https:\/\/doi.org\/10.1007\/s10772-022-09983-8","journal-title":"Int. J. Speech Technol."},{"key":"33_CR9","doi-asserted-by":"publisher","unstructured":"Oralbekova, D., Mamyrbayev, O., Othman, M., Alimhan, K., Zhumazhanov, B., Nuranbayeva, B.: Development of CRF and CTC based end-to-end kazakh speech recognition system. In: Nguyen, N.T., Tran, T.K., Tukayev, U., Hong, TP., Trawi\u0144ski, B., Szczerbicki, E. (eds.) Intelligent Information and Database Systems. ACIIDS 2022. Lecture Notes in Computer Science(), vol. 13757. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-21743-2_41","DOI":"10.1007\/978-3-031-21743-2_41"},{"key":"33_CR10","doi-asserted-by":"publisher","unstructured":"Mamyrbayev, O., Oralbekova, D., Kydyrbekova, A., Turdalykyzy, T., Bekarystankyzy, A.: End-to-end model based on RNN-T for Kazakh speech recognition. In: 2021 3rd International Conference on Computer Communication and the Internet (ICCCI), pp. 163\u2013167 (2021). https:\/\/doi.org\/10.1109\/ICCCI51764.2021.9486811","DOI":"10.1109\/ICCCI51764.2021.9486811"},{"key":"33_CR11","unstructured":"Abulimiti, A., Schultz, T.: Automatic speech recognition for uyghur through multilingual acoustic modeling. In: Proceedings of the Twelfth Language Resources and Evaluation Conference, pp. 6444\u20136449. European Language Resources Association, Marseille, France (2020)"},{"issue":"1","key":"33_CR12","doi-asserted-by":"publisher","first-page":"326","DOI":"10.3390\/app13010326","volume":"13","author":"W Du","year":"2022","unstructured":"Du, W., Maimaitiyiming, Y., Nijat, M., Li, L., Hamdulla, A., Wang, D.: Automatic speech recognition for Uyghur, Kazakh, and Kyrgyz: an overview. Appl. Sci. 13(1), 326 (2022). https:\/\/doi.org\/10.3390\/app13010326","journal-title":"Appl. Sci."},{"key":"33_CR13","doi-asserted-by":"publisher","first-page":"3683","DOI":"10.3390\/s22103683","volume":"22","author":"A Mukhamadiyev","year":"2022","unstructured":"Mukhamadiyev, A., Khujayarov, I., Djuraev, O., Cho, J.: Automatic speech recognition method based on deep learning approaches for Uzbek Language. Sensors 22, 3683 (2022). https:\/\/doi.org\/10.3390\/s22103683","journal-title":"Sensors"},{"key":"33_CR14","doi-asserted-by":"publisher","first-page":"7319","DOI":"10.3390\/s22197319","volume":"22","author":"Z Ren","year":"2022","unstructured":"Ren, Z., Yolwas, N., Slamu, W., Cao, R., Wang, H.: Improving hybrid CTC\/attention architecture for agglutinative language speech recognition. Sensors 22, 7319 (2022). https:\/\/doi.org\/10.3390\/s22197319","journal-title":"Sensors"},{"key":"33_CR15","doi-asserted-by":"publisher","unstructured":"Rathor, S., Jadon, R.S.: Speech recognition and system controlling using Hindi language. In: 2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT), pp. 1\u20136. Kanpur, India (2019). https:\/\/doi.org\/10.1109\/ICCCNT45670.2019.8944641","DOI":"10.1109\/ICCCNT45670.2019.8944641"},{"key":"33_CR16","unstructured":"TechInsider Homepage: https:\/\/www.techinsider.ru\/technologies\/1122303-raspoznavanie-rechi-v-medicine-zachem-nam-eto-nuzhno\/. Last accessed 16 Mar 2023"},{"key":"33_CR17","unstructured":"Sensory Inc. Homepage: https:\/\/www.sensory.com\/. Last accessed 16 Mar 2023"},{"key":"33_CR18","unstructured":"SoapBox Inc. Homepage. https:\/\/www.soapboxlabs.com\/. Last accessed 16 Feb 2023"},{"key":"33_CR19","doi-asserted-by":"publisher","first-page":"108002","DOI":"10.1016\/j.apacoust.2021.108002","volume":"178","author":"V Kadyan","year":"2021","unstructured":"Kadyan, V., Shanawazuddin, S., Singh, A.: Developing children\u2019s speech recognition system for low resource Punjabi language. Appl. Acoustics 178, 108002 (2021). https:\/\/doi.org\/10.1016\/j.apacoust.2021.108002","journal-title":"Appl. Acoustics"},{"key":"33_CR20","doi-asserted-by":"publisher","unstructured":"Jenthe, T., Kris, D.: Transfer Learning for Robust Low-Resource Children\u2019s Speech ASR with Transformers and Source-Filter Warping (2022). https:\/\/doi.org\/10.48550\/arXiv.2206.09396","DOI":"10.48550\/arXiv.2206.09396"},{"key":"33_CR21","doi-asserted-by":"publisher","unstructured":"Rong, T., Lei, W., Bin, M.: Transfer learning for children\u2019s speech recognition, pp. 36\u201339 (2017). https:\/\/doi.org\/10.1109\/IALP.2017.8300540","DOI":"10.1109\/IALP.2017.8300540"},{"key":"33_CR22","unstructured":"Dissertation thesis. https:\/\/jscholarship.library.jhu.edu\/bitstream\/handle\/1774.2\/62766\/WU-THESIS-2020.pdf?sequence=1. Last accessed 2 Feb 2023"},{"key":"33_CR23","doi-asserted-by":"publisher","unstructured":"Dubagunta, S.P., Hande Kabil, S., Magimai.-Doss, M.: Improving children speech recognition through feature learning from raw speech signal. In: ICASSP 2019 \u2013 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5736\u20135740. Brighton, UK (2019). https:\/\/doi.org\/10.1109\/ICASSP.2019.8682826","DOI":"10.1109\/ICASSP.2019.8682826"},{"key":"33_CR24","doi-asserted-by":"publisher","first-page":"101289","DOI":"10.1016\/j.csl.2021.101289","volume":"72","author":"PG Shivakumar","year":"2022","unstructured":"Shivakumar, P.G., Narayanan, S.: End-to-end neural systems for automatic children speech recognition: an empirical study. Comput. Speech Lang. 72, 101289 (2022). https:\/\/doi.org\/10.1016\/j.csl.2021.101289","journal-title":"Comput. Speech Lang."},{"key":"33_CR25","doi-asserted-by":"publisher","unstructured":"Potamianos, A., Narayanan, S., Lee, S.: Automatic speech recognition for children (1997). https:\/\/doi.org\/10.21437\/Eurospeech.1997-623","DOI":"10.21437\/Eurospeech.1997-623"},{"key":"33_CR26","unstructured":"Ignatenko, G.S.: Classification of audio signals using neural networks. In: Ignatenko, G.S., Lamchanovsky, A.G. (eds.) Text: direct \/\/ Young scientist. - No. 48 (286), pp. 23\u201325 (2019). https:\/\/moluch.ru\/archive\/286\/64455\/"},{"key":"33_CR27","first-page":"32","volume":"7","author":"O Mamyrbayev","year":"2022","unstructured":"Mamyrbayev, O., Oralbekova, D., Othman, M., Turdalykyzy, T., Zhumazhanov, B., Mukhsina, K.: Investigation of insertion-based speech recognition method. Int. J. Signal Process. 7, 32\u201335 (2022)","journal-title":"Int. J. Signal Process."},{"key":"33_CR28","unstructured":"Gu, J., Bradbury, J., Xiong, C., Li, V.O., Socher R.: Non-autoregressive neural machine translation. arXiv preprint arXiv:1711.02281 (2017)"},{"key":"33_CR29","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1109\/LSP.2020.3044547","volume":"28","author":"N Chen","year":"2021","unstructured":"Chen, N., Watanabe, S., Villalba, J., Zelasko, P., Dehak, N.: Non-autoregressive transformer for speech recognition. IEEE Signal Process. Lett. 28, 121\u2013125 (2021)","journal-title":"IEEE Signal Process. Lett."},{"key":"33_CR30","doi-asserted-by":"publisher","unstructured":"Fujita, Y., Watanabe, S., Omachi, M., Chan, X.: Insertion-Based Modeling for End-to-End Automatic Speech Recognition. INTERSPEECH 2020 (2020). https:\/\/doi.org\/10.48550\/arXiv.2005.13211","DOI":"10.48550\/arXiv.2005.13211"}],"container-title":["Communications in Computer and Information Science","Advances in Computational Collective Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-41774-0_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T06:34:09Z","timestamp":1695278049000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41774-0_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031417733","9783031417740"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41774-0_33","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCCI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Collective Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Budapest","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hungary","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccci2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iccci.pwr.edu.pl\/2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"218","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"59","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.01","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1.86","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}