{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:01:52Z","timestamp":1786978912567,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030878016","type":"print"},{"value":"9783030878023","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-87802-3_40","type":"book-chapter","created":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T19:36:52Z","timestamp":1632253012000},"page":"437-447","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["USC: An Open-Source Uzbek Speech Corpus and Initial Speech Recognition Experiments"],"prefix":"10.1007","author":[{"given":"Muhammadjon","family":"Musaev","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saida","family":"Mussakhojayeva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ilyos","family":"Khujayorov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yerbolat","family":"Khassanov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mannon","family":"Ochilov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huseyin","family":"Atakan Varol","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,22]]},"reference":[{"key":"40_CR1","unstructured":"Speechocean\u2019s Uzbek speech corpus. http:\/\/en.speechocean.com\/datacenter\/details\/1847.html. Accessed 21 May 2021"},{"key":"40_CR2","unstructured":"Uzbek language. https:\/\/en.wikipedia.org\/wiki\/Uzbek_language. Accessed 20 May 2021"},{"key":"40_CR3","unstructured":"Voxforge. http:\/\/www.voxforge.org\/. Accessed 11 May 2021"},{"issue":"6","key":"40_CR4","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: the shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82\u201397 (2012)","journal-title":"IEEE Signal Process. Mag."},{"key":"40_CR5","doi-asserted-by":"crossref","unstructured":"Abdel-Hamid, O., Mohamed, A., Jiang, H., Deng, L., Penn, G., Yu, D.: Convolutional neural networks for speech recognition. IEEE ACM Trans. Audio Speech Lang. Process. 22(10), 1533\u20131545 (2014)","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"40_CR6","unstructured":"Ardila, R., et al.: Common voice: a massively-multilingual speech corpus. In: LREC, pp. 4218\u20134222. ELRA (2020)"},{"key":"40_CR7","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.specom.2013.07.008","volume":"56","author":"L Besacier","year":"2014","unstructured":"Besacier, L., Barnard, E., Karpov, A., Schultz, T.: Automatic speech recognition for under-resourced languages: a survey. Speech Commun. 56, 85\u2013100 (2014)","journal-title":"Speech Commun."},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"Bu, H., Du, J., Na, X., Wu, B., Zheng, H.: AISHELL-1: an open-source Mandarin speech corpus and a speech recognition baseline. In: Proceedings of the O-COCOSDA, pp. 1\u20135. IEEE (2017)","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"40_CR9","doi-asserted-by":"crossref","unstructured":"Doumbouya, M., Einstein, L., Piech, C.: Using radio archives for low-resource speech recognition: towards an intelligent virtual assistant for illiterate users. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 14757\u201314765. AAAI Press (2021)","DOI":"10.1609\/aaai.v35i17.17733"},{"key":"40_CR10","unstructured":"Gales, M.J.F., Knill, K.M., Ragni, A., Rath, S.P.: Speech recognition and keyword spotting for low-resource languages: Babel project research at CUED. In: Proceedings of the Workshop on Spoken Language Technologies for Under-Resourced Languages (SLTU), pp. 16\u201323. ISCA (2014)"},{"key":"40_CR11","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F.J., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the International Conference on Machine Learning (ICML), Pittsburgh, Pennsylvania, USA, 25\u201329 June 2006, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"40_CR12","unstructured":"Graves, A., Jaitly, N.: Towards end-to-end speech recognition with recurrent neural networks. In: Proceedings of the International Conference on Machine Learning (ICML), Beijing, China, 21\u201326 June 2014, vol. 32, pp. 1764\u20131772 (2014)"},{"key":"40_CR13","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A., Hinton, G.E.: Speech recognition with deep recurrent neural networks. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6645\u20136649. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"40_CR14","doi-asserted-by":"crossref","unstructured":"Gulati, A., et al.: Conformer: convolution-augmented transformer for speech recognition. In: Proceedings of INTERSPEECH, pp. 5036\u20135040. ISCA (2020)","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"40_CR15","unstructured":"G\u00fcl\u00e7ehre, \u00c7., et al.: On using monolingual corpora in neural machine translation. CoRR abs\/1503.03535 (2015). http:\/\/arxiv.org\/abs\/1503.03535"},{"issue":"8","key":"40_CR16","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"40_CR17","doi-asserted-by":"crossref","unstructured":"Khassanov, Y., Mussakhojayeva, S., Mirzakhmetov, A., Adiyev, A., Nurpeiissov, M., Varol, H.A.: A crowdsourced open-source Kazakh speech corpus and initial speech recognition baseline. In: Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics, pp. 697\u2013706. Association for Computational Linguistics, April 2021","DOI":"10.18653\/v1\/2021.eacl-main.58"},{"key":"40_CR18","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: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4835\u20134839 (2017)","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"40_CR19","doi-asserted-by":"crossref","unstructured":"Ko, T., Peddinti, V., Povey, D., Khudanpur, S.: Audio augmentation for speech recognition. In: Proceedings of INTERSPEECH, pp. 3586\u20133589 (2015)","DOI":"10.21437\/Interspeech.2015-711"},{"key":"40_CR20","doi-asserted-by":"crossref","unstructured":"Musaev, M., Khujayorov, I., Ochilov, M.: Image approach to speech recognition on CNN. In: Proceedings of the International Symposium on Computer Science and Intelligent Control (ISCSIC), pp. 57:1\u201357:6. ACM (2019)","DOI":"10.1145\/3386164.3389100"},{"key":"40_CR21","doi-asserted-by":"crossref","unstructured":"Musaev, M., Khujayorov, I., Ochilov, M.: Development of integral model of speech recognition system for Uzbek language. In: Proceedings of the IEEE International Conference on Application of Information and Communication Technologies (AICT), pp. 1\u20136. IEEE (2020)","DOI":"10.1109\/AICT50176.2020.9368719"},{"key":"40_CR22","doi-asserted-by":"crossref","unstructured":"Musaev, M., Khujayorov, I., Ochilov, M.: The use of neural networks to improve the recognition accuracy of explosive and unvoiced phonemes in Uzbek language. In: Proceedings of the Information Communication Technologies Conference (ICTC), pp. 231\u2013234. IEEE (2020)","DOI":"10.1109\/ICTC49638.2020.9123309"},{"key":"40_CR23","series-title":"Advances in Intelligent Systems and Computing","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1007\/978-3-030-68004-6_28","volume-title":"11th World Conference \u201cIntelligent System for Industrial Automation\u201d (WCIS-2020)","author":"M Musaev","year":"2021","unstructured":"Musaev, M., Khujayorov, I., Ochilov, M.: Automatic recognition of Uzbek speech based on integrated neural networks. In: Aliev, R.A., Yusupbekov, N.R., Kacprzyk, J., Pedrycz, W., Sadikoglu, F.M. (eds.) WCIS 2020. AISC, vol. 1323, pp. 215\u2013223. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-68004-6_28"},{"key":"40_CR24","doi-asserted-by":"crossref","unstructured":"Mussakhojayeva, S., Janaliyeva, A., Mirzakhmetov, A., Khassanov, Y., Varol, H.A.: KazakhTTS: an open-source Kazakh text-to-speech synthesis dataset. CoRR abs\/2104.08459 (2021). https:\/\/arxiv.org\/abs\/2104.08459","DOI":"10.21437\/Interspeech.2021-2124"},{"key":"40_CR25","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: Librispeech: an ASR corpus based on public domain audio books. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5206\u20135210. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"40_CR26","doi-asserted-by":"crossref","unstructured":"Park, D.S., et al.: SpecAugment: a simple data augmentation method for automatic speech recognition. In: Proceedings of INTERSPEECH, pp. 2613\u20132617 (2019)","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"40_CR27","doi-asserted-by":"crossref","unstructured":"Povey, D., et al.: Semi-orthogonal low-rank matrix factorization for deep neural networks. In: Proceedings of INTERSPEECH, pp. 3743\u20133747 (2018)","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"40_CR28","unstructured":"Povey, D., et al.: The Kaldi speech recognition toolkit. In: Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding (2011)"},{"key":"40_CR29","doi-asserted-by":"crossref","unstructured":"Povey, D., et al.: Purely sequence-trained neural networks for ASR based on lattice-free MMI. In: Proceedings of INTERSPEECH, pp. 2751\u20132755 (2016)","DOI":"10.21437\/Interspeech.2016-595"},{"key":"40_CR30","unstructured":"ReadBeyond: Aeneas. https:\/\/www.readbeyond.it\/aeneas\/"},{"key":"40_CR31","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1007\/978-3-319-99579-3_21","volume-title":"Speech and Computer","author":"F Hernandez","year":"2018","unstructured":"Hernandez, F., Nguyen, V., Ghannay, S., Tomashenko, N., Est\u00e8ve, Y.: TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation. In: Karpov, A., Jokisch, O., Potapova, R. (eds.) SPECOM 2018. LNCS (LNAI), vol. 11096, pp. 198\u2013208. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-99579-3_21"},{"key":"40_CR32","unstructured":"Solak, I.: The M-AILABS speech dataset. https:\/\/www.caito.de\/2019\/01\/the-m-ailabs-speech-dataset\/. Accessed 11 May 2021"},{"key":"40_CR33","unstructured":"Telegram FZ LLC and Telegram Messenger Inc.: Telegram. https:\/\/telegram.org"},{"key":"40_CR34","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the Annual Conference on Neural Information Processing Systems, 4\u20139 December 2017, Long Beach, CA, USA, pp. 5998\u20136008 (2017)"},{"key":"40_CR35","doi-asserted-by":"crossref","unstructured":"Watanabe, S., et al.: ESPnet: end-to-end speech processing toolkit. In: Proceedings of INTERSPEECH, Hyderabad, India, 2\u20136 September 2018, pp. 2207\u20132211 (2018)","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"40_CR36","series-title":"Signals and Communication Technology","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-5779-3","volume-title":"Automatic Speech Recognition","author":"D Yu","year":"2015","unstructured":"Yu, D., Deng, L.: Automatic Speech Recognition. SCT, Springer, London (2015). https:\/\/doi.org\/10.1007\/978-1-4471-5779-3"},{"key":"40_CR37","unstructured":"Zeiler, M.D.: ADADELTA: an adaptive learning rate method. CoRR abs\/1212.5701 (2012). http:\/\/arxiv.org\/abs\/1212.5701"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87802-3_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T17:01:18Z","timestamp":1673283678000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87802-3_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030878016","9783030878023"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87802-3_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"22 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"St Petersburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2021\/","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":"163","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":"74","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":"45% - 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":"3.5","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":"5.5","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held online due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}