{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T12:32:36Z","timestamp":1762432356803,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031390586"},{"type":"electronic","value":"9783031390593"}],"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\/978-3-031-39059-3_17","type":"book-chapter","created":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T13:01:37Z","timestamp":1690722097000},"page":"254-268","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Exploring ASR Models in\u00a0Low-Resource Languages: Use-Case the\u00a0Macedonian Language"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4879-9870","authenticated-orcid":false,"given":"Konstantin","family":"Bogdanoski","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3982-3330","authenticated-orcid":false,"given":"Kostadin","family":"Mishev","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5028-3841","authenticated-orcid":false,"given":"Monika","family":"Simjanoska","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3105-6010","authenticated-orcid":false,"given":"Dimitar","family":"Trajanov","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,7,31]]},"reference":[{"key":"17_CR1","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: Wav2vec 2.0: a framework for self-supervised learning of speech representations. Adv. Neural Inf. Process. Syst. 33, 12449\u201312460 (2020)"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Bogdanoski, K., Mishev, K., Trajanov, D.: Blanket clusterer: a tool for automating the clustering in unsupervised learning (2022)","DOI":"10.5220\/0011276000003277"},{"key":"17_CR3","unstructured":"Dekker, R.: The importance of having data-sets (2006)"},{"key":"17_CR4","unstructured":"Developers, T.: Tensorflow. Zenodo (2021)"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Dong, Q., et al.: Listen, understand and translate: triple supervision decouples end-to-end speech-to-text translation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 12749\u201312759 (2021)","DOI":"10.1609\/aaai.v35i14.17509"},{"key":"17_CR6","unstructured":"Haji\u010d, J.: Disambiguation of rich inflection: computational morphology of Czech. Karolinum (2004)"},{"key":"17_CR7","unstructured":"Hoffmann, R., Shpilewsky, E., Lobanov, B.M., Ronzhin, A.L.: Development of multi-voice and multi-language text-to-speech (TTS) and speech-to-text (STT) conversion system (languages: Belorussian, Polish, Russian). In: 9th Conference Speech and Computer (2004)"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Hrinchuk, O., et al.: Nvidia nemo offline speech translation systems for IWSLT 2022. In: Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022), pp. 225\u2013231 (2022)","DOI":"10.18653\/v1\/2022.iwslt-1.18"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Kriman, S., et al.: QuartzNet: deep automatic speech recognition with 1D time-channel separable convolutions. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6124\u20136128. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053889"},{"key":"17_CR10","unstructured":"Kuchaiev, O., et al.: NeMo: a toolkit for building AI applications using neural modules. arXiv preprint arXiv:1909.09577 (2019)"},{"key":"17_CR11","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1016\/j.neunet.2022.01.016","volume":"148","author":"C Mi","year":"2022","unstructured":"Mi, C., Xie, L., Zhang, Y.: Improving data augmentation for low resource speech-to-text translation with diverse paraphrasing. Neural Netw. 148, 194\u2013205 (2022)","journal-title":"Neural Netw."},{"issue":"19","key":"17_CR12","doi-asserted-by":"publisher","first-page":"6882","DOI":"10.3390\/app10196882","volume":"10","author":"K Mishev","year":"2020","unstructured":"Mishev, K., Karovska Ristovska, A., Trajanov, D., Eftimov, T., Simjanoska, M.: MAKEDONKA: applied deep learning model for text-to-speech synthesis in Macedonian language. Appl. Sci. 10(19), 6882 (2020)","journal-title":"Appl. Sci."},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Mitreska, M., Pavlov, T., Mishev, K., Simjanoska, M.: xAMR: Cross-lingual AMR end-to-end pipeline (2022)","DOI":"10.5220\/0011276500003277"},{"key":"17_CR14","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1007\/3-540-46154-X_26","volume-title":"Text, Speech and Dialogue","author":"J Nouza","year":"2002","unstructured":"Nouza, J.: Strategies for developing a real-time continuous speech recognition system for Czech language. In: Sojka, P., Kope\u010dek, I., Pala, K. (eds.) TSD 2002. LNCS (LNAI), vol. 2448, pp. 189\u2013196. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-46154-X_26"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Nouza, J., Drabkova, J.: Combining lexical and morphological knowledge in language model for inflectional (Czech) language. In: Seventh International Conference on Spoken Language Processing (2002)","DOI":"10.21437\/ICSLP.2002-233"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Nouza, J., Safarik, R., Cerva, P.: ASR for south Slavic languages developed in almost automated way. In: INTERSPEECH, pp. 3868\u20133872 (2016)","DOI":"10.21437\/Interspeech.2016-747"},{"key":"17_CR17","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":"17_CR18","unstructured":"Pytorch, A.D.I.: Pytorch (2018)"},{"issue":"1","key":"17_CR19","first-page":"253","volume":"3","author":"BR Reddy","year":"2013","unstructured":"Reddy, B.R., Mahender, E.: Speech to text conversion using android platform. Int. J. Eng. Res. Appl. (IJERA) 3(1), 253\u2013258 (2013)","journal-title":"Int. J. Eng. Res. Appl. (IJERA)"},{"key":"17_CR20","unstructured":"Ronzhin, A.L., Karpov, A.A.: Implementation of morphemic analysis for Russian speech recognition. In: 9th Conference Speech and Computer (2004)"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Schultz, T.: GlobalPhone: a multilingual speech and text database developed at Karlsruhe university. In: Seventh International Conference on Spoken Language Processing (2002)","DOI":"10.21437\/ICSLP.2002-151"},{"key":"17_CR22","unstructured":"Tamburini, F.: Playing with nemo for building an automatic speech recogniser for Italian. In: CLiC-it (2021)"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Tacotron: towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135 (2017)","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Watanabe, S., et al.: ESPNet: end-to-end speech processing toolkit. arXiv preprint arXiv:1804.00015 (2018)","DOI":"10.21437\/Interspeech.2018-1456"},{"issue":"2","key":"17_CR25","doi-asserted-by":"publisher","first-page":"179","DOI":"10.3390\/sym11020179","volume":"11","author":"C Yu","year":"2019","unstructured":"Yu, C., Chen, Y., Li, Y., Kang, M., Xu, S., Liu, X.: Cross-language end-to-end speech recognition research based on transfer learning for the low-resource Tujia language. Symmetry 11(2), 179 (2019)","journal-title":"Symmetry"},{"key":"17_CR26","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-5779-3","volume-title":"Automatic Speech Recognition","author":"D Yu","year":"2016","unstructured":"Yu, D., Deng, L.: Automatic Speech Recognition, vol. 1. Springer, Heidelbergt (2016). https:\/\/doi.org\/10.1007\/978-1-4471-5779-3"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Learning to speak fluently in a foreign language: multilingual speech synthesis and cross-language voice cloning. arXiv preprint arXiv:1907.04448 (2019)","DOI":"10.21437\/Interspeech.2019-2668"}],"container-title":["Communications in Computer and Information Science","Deep Learning Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-39059-3_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T13:05:18Z","timestamp":1690722318000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-39059-3_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031390586","9783031390593"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-39059-3_17","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":"31 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DeLTA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Deep Learning Theory and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rome","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"13 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"delta2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/delta.scitevents.org\/","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":"PRIMORIS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"42","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":"9","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":"22","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":"21% - 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":"4","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)"}}]}}