{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,12]],"date-time":"2025-07-12T01:13:01Z","timestamp":1752282781879,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031404979"},{"type":"electronic","value":"9783031404986"}],"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\/978-3-031-40498-6_29","type":"book-chapter","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T23:02:34Z","timestamp":1692745354000},"page":"328-338","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Transfer Learning of\u00a0Transformer-Based Speech Recognition Models from\u00a0Czech to\u00a0Slovak"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3889-8069","authenticated-orcid":false,"given":"Jan","family":"Lehe\u010dka","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4761-1645","authenticated-orcid":false,"given":"Josef V.","family":"Psutka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0764-3207","authenticated-orcid":false,"given":"Josef","family":"Psutka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,23]]},"reference":[{"key":"29_CR1","unstructured":"Ardila, R., et al.: Common voice: a massively-multilingual speech corpus. In: Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pp. 4211\u20134215 (2020)"},{"key":"29_CR2","doi-asserted-by":"publisher","unstructured":"Babu, A., et al.: XLS-R: self-supervised cross-lingual speech representation learning at scale. In: Proceedings of Interspeech 2022, pp. 2278\u20132282 (2022). https:\/\/doi.org\/10.21437\/Interspeech.2022-143","DOI":"10.21437\/Interspeech.2022-143"},{"key":"29_CR3","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. 12449\u201312460 (2020)"},{"key":"29_CR4","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":"29_CR5","unstructured":"Heafield, K.: KenLM: faster and smaller language model queries. In: Proceedings of the Sixth Workshop on Statistical Machine Translation, pp. 187\u2013197 (2011)"},{"key":"29_CR6","doi-asserted-by":"publisher","unstructured":"Lehe\u010dka, J., \u0160vec, J., Pra\u017e\u00e1k, A., Psutka, J.V.: Exploring capabilities of monolingual audio transformers using large datasets in automatic speech recognition of Czech. In: Proceedings of Interspeech 2022, pp. 1831\u20131835 (2022). https:\/\/doi.org\/10.21437\/Interspeech.2022-10439","DOI":"10.21437\/Interspeech.2022-10439"},{"key":"29_CR7","unstructured":"MALACH project (2006). https:\/\/malach.umiacs.umd.edu\/"},{"key":"29_CR8","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1007\/978-3-642-00525-1_24","volume-title":"Multimodal Signals: Cognitive and Algorithmic Issues","author":"M Mirilovi\u010d","year":"2009","unstructured":"Mirilovi\u010d, M., Juh\u00e1r, J., \u010ci\u017em\u00e1r, A.: Comparison of grapheme and phoneme based acoustic modeling in LVCSR task in Slovak. In: Esposito, A., Hussain, A., Marinaro, M., Martone, R. (eds.) Multimodal Signals: Cognitive and Algorithmic Issues. LNCS (LNAI), vol. 5398, pp. 242\u2013247. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-00525-1_24"},{"key":"29_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1007\/978-3-642-12397-9_19","volume-title":"Development of Multimodal Interfaces: Active Listening and Synchrony","author":"J Nouza","year":"2010","unstructured":"Nouza, J., Zdansky, J., Cerva, P., Silovsky, J.: Challenges in speech processing of slavic languages (case studies in speech recognition of Czech and Slovak). In: Esposito, A., Campbell, N., Vogel, C., Hussain, A., Nijholt, A. (eds.) Development of Multimodal Interfaces: Active Listening and Synchrony. LNCS, vol. 5967, pp. 225\u2013241. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-12397-9_19"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Ott, M., Edunov, S., Baevski, A., Fan, A., Gross, S., Ng, N., Grangier, D., Auli, M.: fairseq: a fast, extensible toolkit for sequence modeling. In: Proceedings of NAACL-HLT 2019: Demonstrations (2019)","DOI":"10.18653\/v1\/N19-4009"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Psutka, J., Ircing, P., Psutka, J.V., Haji\u010d, J., Byrne, W., M\u00edrovsk\u00fd, J.: Automatic transcription of Czech, Russian and Slovak spontaneous speech in the MALACH project. In: Eurospeech 2005, pp. 1349\u20131352. ISCA (2005)","DOI":"10.21437\/Interspeech.2005-489"},{"key":"29_CR12","unstructured":"Psutka, J.V., Psutka, J., Radov\u00e1, V., Ircing, P., Matou\u0161ek, J., M\u00fcller, L.: USC-SFI MALACH interviews and transcripts Czech (2014). https:\/\/catalog.ldc.upenn.edu\/LDC2014S04"},{"key":"29_CR13","doi-asserted-by":"publisher","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision (2022). https:\/\/doi.org\/10.48550\/ARXIV.2212.04356, arXiv:2212.04356","DOI":"10.48550\/ARXIV.2212.04356"},{"key":"29_CR14","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020). http:\/\/jmlr.org\/papers\/v21\/20-074.html"},{"key":"29_CR15","unstructured":"UCL. https:\/\/www.phon.ucl.ac.uk\/home\/sampa\/"},{"key":"29_CR16","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS 2017, pp. 6000\u20136010. Curran Associates Inc., Red Hook (2017)"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.: VoxPopuli: a large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 993\u20131003. Association for Computational Linguistics, Online (2021). https:\/\/aclanthology.org\/2021.acl-long.80","DOI":"10.18653\/v1\/2021.acl-long.80"}],"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\/978-3-031-40498-6_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T23:06:34Z","timestamp":1692745594000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-40498-6_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031404979","9783031404986"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-40498-6_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"23 August 2023","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":"Pilsen","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.kiv.zcu.cz\/tsd2023\/index.php","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":"CMS & back-office system","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"64","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":"31","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":"48% - 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":"2.56","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)"}}]}}