{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T00:07:38Z","timestamp":1767139658344,"version":"build-2238731810"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819759330","type":"print"},{"value":"9789819759347","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-5934-7_28","type":"book-chapter","created":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T04:02:36Z","timestamp":1723435356000},"page":"330-340","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Study of Kazakh Speech Recognition in Hiformer Model"],"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\/0000-0003-1178-6400","authenticated-orcid":false,"given":"Turdybek","family":"Kurmetkan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4975-6493","authenticated-orcid":false,"given":"Dina","family":"Oralbekova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2153-7620","authenticated-orcid":false,"given":"Nurdaulet","family":"Zhumazhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,13]]},"reference":[{"key":"28_CR1","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.patrec.2018.05.018","volume":"118","author":"G Yao","year":"2019","unstructured":"Yao, G., Lei, T., Zhong, J.: A review of convolutional-neural-network-based action recognition. Pattern Recogn. Lett. 118, 14\u201322 (2019)","journal-title":"Pattern Recogn. Lett."},{"key":"28_CR2","unstructured":"Vaswani, N., et al.: Attention is all you need. In: Proceedings of NeurIPS, arxiv: 1706.0376 (2017)"},{"key":"28_CR3","unstructured":"Choi, H., Lee, J., Kim, W., Lee, J., Heo, H., Lee, K.: Neural analysis and synthesis: reconstructing speech from self-supervised representations. In: Proceedings of NeurIPS (2021)"},{"key":"28_CR4","doi-asserted-by":"publisher","unstructured":"Mamyrbayev, O., Oralbekova, D., Alimhan, K.,\u00a0Turdalykyzy, T., Othman, M.: A study of transformer-based end-to-end speech recognition system for Kazakh language. In: Proceedings of Springer Nature (2022). https:\/\/doi.org\/10.1038\/s41598-022-12260-y","DOI":"10.1038\/s41598-022-12260-y"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Wu, X., Lu, H., Li, K., Wu, Z., Liu, X., Meng, H.: Hiformer: Sequence Modeling Networks with Hierarchical Attention Mechanisms. In: Publication in IEEE\/ACM Transactions on Audio, Speech and Language Processing 6 (2023)","DOI":"10.1109\/TASLP.2023.3313428"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Chan, W., Jaitly, N., Le, Q., Vinyals, O.: Listen, attend and spell: a neural network for large vocabulary conversational speech recognition. In: Proceedings of the 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, China, 20\u201325 March 2016 (2016)","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Mamyrbayev, O., Turdalyuly, M., Mekebayev, N., Alimhan, K., Kydyrbekova, A., Turdalykyzy, T.: Automatic recognition of Kazakh speech using deep neural networks. In: ACIIDS, Lecture Notes in Computer Science, pp. 465\u2013474 (2019)","DOI":"10.1007\/978-3-030-14802-7_40"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Kozhirbayev, Z., Islamgozhayev, T.: Cascade speech translation for the Kazakh language. Appl. Sci. (2023)","DOI":"10.3390\/app13158900"},{"key":"28_CR9","unstructured":"Amirgaliyev, E.,\u00a0Kuanyshbay, D.,\u00a0Baimuratov, O.: Development of automatic speech recognition for Kazakh language using transfer learning. Int. J. Adv. Trends Comput. Sci. Eng. (2020)"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Meng, W., Yolwas,\u00a0N.: A study of speech recognition for Kazakh based on unsupervised pre-training. Sensors (2023)","DOI":"10.3390\/s23020870"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Bapna, A., Chen, M., Firat, O., et al.: Training deeper neural machine translation models with transparent attention. In: Proceedings of EMNLP (2018)","DOI":"10.18653\/v1\/D18-1338"},{"key":"28_CR12","unstructured":"Srivastava, R., Greff, K., Schmidhuber, J.: Training very deep networks. In: Proceedings of NeurIPS (2015)"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: GTRANS: grouping and fusing transformer layers for neural machine translation. IEEE\/ACM Trans. Audio, Speech Lang. Process (2022)","DOI":"10.1109\/TASLP.2022.3221040"},{"key":"28_CR14","unstructured":"Chung, J., Ahn, S., Bengio, Y.: Hierarchical multiscale recurrent neural networks. In: Proceedings of ICLR (2017)"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Lu, H., Sak, H., et al.: Transformer transducer: a streamable speech recognition model with transformer encoders and RNNT loss. In: Proceedings of ICASSP (2020)","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Povey, D., Hadian, H., Ghahremani, P., Li, K., Khudanpur, S.: A timerestricted self-attention layer for ASR. In: Proceedings of ICASSP (2018)","DOI":"10.1109\/ICASSP.2018.8462497"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Wang, Y., Mohamed, A., Le, D., et al.: Transformer-based acoustic modeling for hybrid speech recognition In: Proceedings of ICASSP (2020)","DOI":"10.1109\/ICASSP40776.2020.9054345"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Sang, J., Nurmemet, Y.: Knowledge distillation for end-to-end speech recognition based on Conformer model. In: International Symposium on Robotics (2022)","DOI":"10.1117\/12.2659711"},{"key":"28_CR19","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. In: Advances in Neural Information Processing Systems, vol. 33, pp. 12:449\u201312:460 (2020)"},{"key":"28_CR20","doi-asserted-by":"crossref","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)","DOI":"10.1109\/ICCCI51764.2021.9486811"}],"updated-by":[{"DOI":"10.1007\/978-981-97-5934-7_30","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000}}],"container-title":["Communications in Computer and Information Science","Recent Challenges in Intelligent Information and Database Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5934-7_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T01:06:01Z","timestamp":1733101561000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5934-7_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819759330","9789819759347"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5934-7_28","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"13 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"3 December 2024","order":2,"name":"change_date","label":"Change Date","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Correction","order":3,"name":"change_type","label":"Change Type","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"A correction has been published.","order":4,"name":"change_details","label":"Change Details","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":"Ras Al Khaimah","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Arab Emirates","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 April 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 April 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aciids2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aciids.pwr.edu.pl\/2024\/index.php#about","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}