{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T11:32:27Z","timestamp":1743075147415,"version":"3.40.3"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030835262"},{"type":"electronic","value":"9783030835279"}],"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\/978-3-030-83527-9_41","type":"book-chapter","created":{"date-parts":[[2021,8,29]],"date-time":"2021-08-29T23:04:59Z","timestamp":1630278299000},"page":"481-488","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Incorporation of Iterative Self-supervised Pre-training in the Creation of the ASR System for the Tatar Language"],"prefix":"10.1007","author":[{"given":"Aidar","family":"Khusainov","sequence":"first","affiliation":[]},{"given":"Dzhavdet","family":"Suleymanov","sequence":"additional","affiliation":[]},{"given":"Ilnur","family":"Muhametzyanov","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,8,30]]},"reference":[{"key":"41_CR1","unstructured":"Commonvoice (2021). https:\/\/commonvoice.mozilla.org\/"},{"key":"41_CR2","unstructured":"Commonvoice tatar benchmark (2021). https:\/\/paperswithcode.com\/sota\/speech-recognition-on-common-voice-tatar"},{"key":"41_CR3","unstructured":"Fair-seq, wav2vec 2.0 pytorch example (2021). https:\/\/github.com\/pytorch\/fairseq\/tree\/master\/examples\/wav2vec"},{"key":"41_CR4","unstructured":"Silero vad: pre-trained enterprise-grade voice activity detector (vad), number detector and language classifier (2021). https:\/\/github.com\/snakers4\/silero-vad\/"},{"key":"41_CR5","unstructured":"Baevski, A., Zhou, H., Mohamed, A., Auli, M.: Wav2vec 2.0: a framework for self-supervised learning of speech representations. In: Proceedings of NeurIPS (2020)"},{"key":"41_CR6","unstructured":"Baevski, A., Auli, M., Mohamed, A.: Effectiveness of self-supervised pre-training for speech recognition. CoRR abs\/1911.03912 (2019). http:\/\/arxiv.org\/abs\/1911.03912"},{"key":"41_CR7","doi-asserted-by":"crossref","unstructured":"Graves, A., Fernandez, S., Gomez, G.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, Pittsburgh, PA, USA (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"41_CR8","unstructured":"Heafield, K.: KenLM: faster and smaller language model queries. In: Proceedings of the Sixth Workshop on Statistical Machine Translation, pp. 187\u2013197. Association for Computational Linguistics, Edinburgh, July 2011. https:\/\/www.aclweb.org\/anthology\/W11-2123"},{"key":"41_CR9","unstructured":"Kahn, J., et al.: Libri-light: a benchmark for ASR with limited or no supervision. CoRR abs\/1912.07875 (2019). http:\/\/arxiv.org\/abs\/1912.07875"},{"key":"41_CR10","doi-asserted-by":"crossref","unstructured":"Kawakami, K., Wang, L., Dyer, C., Blunsom, P., van den Oord, A.: Learning robust and multilingual speech representations (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.106"},{"key":"41_CR11","unstructured":"Khusainov, A.: Design and creation of speech corpora for the Tatar speech recognition and synthesis tasks. In: Proceedings of the 3rd International Conference on Turkic Languages Processing, Kazan, Russia, pp. 475\u2013484 (2015)"},{"key":"41_CR12","unstructured":"Khusainov, A.: Instrument dlya rasrpredelennogo sozdaniya annotirovannyh korpusov. In: Proceedings of the 8th International Conference on Turkic Languages Processin, Ufa, Russia (2020)"},{"key":"41_CR13","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/978-3-319-64206-2_21","volume-title":"Text, Speech, and Dialogue","author":"A Khusainov","year":"2017","unstructured":"Khusainov, A.: Recent results in speech recognition for the Tatar language. In: Ek\u0161tein, K., Matou\u0161ek, V. (eds.) TSD 2017. LNCS (LNAI), vol. 10415, pp. 183\u2013191. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-64206-2_21"},{"key":"41_CR14","doi-asserted-by":"crossref","unstructured":"Schneider, S., Baevski, A., Collobert, R., Auli, M.: wav2vec: unsupervised pre-training for speech recognition. CoRR abs\/1904.05862 (2019). http:\/\/arxiv.org\/abs\/1904.05862","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"41_CR15","unstructured":"Suleymanov, D., Khakimov, B., Gilmullin, R.: Korpus tatarskogo yazyka: konceptualnye i lingvisticheskiy aspekty. Vestnik TGGPU, pp. 211\u2013216 (2011)"}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-83527-9_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,29]],"date-time":"2021-08-29T23:16:37Z","timestamp":1630278997000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-83527-9_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030835262","9783030835279"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-83527-9_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"30 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TSD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Text, Speech, and Dialogue","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Olomouc","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","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":"6 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.kiv.zcu.cz\/tsd2021\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"TSDEngine 3.2","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"101","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":"29","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":"17","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":"29% - 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","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":"2,93","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)"}}]}}