{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T11:17:24Z","timestamp":1760267844626,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031779602"},{"type":"electronic","value":"9783031779619"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-77961-9_4","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T13:54:23Z","timestamp":1732197263000},"page":"57-68","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Towards a Livvi-Karelian End-to-End ASR System"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1264-4458","authenticated-orcid":false,"given":"Irina","family":"Kipyatkova","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1196-1117","authenticated-orcid":false,"given":"Ildar","family":"Kagirov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4344-2330","authenticated-orcid":false,"given":"Mikhail","family":"Dolgushin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5645-9441","authenticated-orcid":false,"given":"Alexandra","family":"Rodionova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"4_CR1","volume-title":"Towards openly multilingual policies and practices: Assessing minority language maintenance in Europe","author":"J Laakso","year":"2016","unstructured":"Laakso, J., Sarhimaa, A., \u00c5kermark, S.S., Toivanen, R.: Towards openly multilingual policies and practices: Assessing minority language maintenance in Europe. Multilingual Matters, Bristol (2016)"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Joshi, P., Santy, S., Budhiraja, A., Bali, K., Choudhury, K.: The state and fate of linguistic diversity and inclusion in the NLP world. In: Proceedings of the LREC 2012 \u2013 58th Annual Meeting of the Association for Computational Linguistics, pp. 6282\u20136293. Virtual Conference, July (2020)","DOI":"10.18653\/v1\/2020.acl-main.560"},{"issue":"3","key":"4_CR3","first-page":"1","volume":"6","author":"EM Bender","year":"2011","unstructured":"Bender, E.M.: On achieving and evaluating language-independence in NLP. Linguis. Issues Lang. Technol. 6(3), 1\u201326 (2011)","journal-title":"Linguis. Issues Lang. Technol."},{"key":"4_CR4","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":"4_CR5","doi-asserted-by":"crossref","unstructured":"Conneau, A., Baevski, A., Collobert, R., Mohamed, A., Auli, M.: Unsupervised cross-lingual representation learning for speech recognition. In: Proceedings of the Interspeech 2021, pp. 2426\u20132430 (2021)","DOI":"10.21437\/Interspeech.2021-329"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Babu, A., et al.: XLS-R: self-supervised cross-lingual speech representation learning at scale. In: Proceedings of the Interspeech 2022, pp. 2278\u20132282 (2022)","DOI":"10.21437\/Interspeech.2022-143"},{"key":"4_CR7","unstructured":"Pratap, V., et al.: Scaling speech technology to 1,000+ languages. J. Mach. Learn. Res. 25(97), 1\u201352 (2024)"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Poth, C., et al.: Adapters: a unified library for parameter-efficient and modular transfer learning. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 149\u2013160 (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.13"},{"key":"4_CR9","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Chung, Y.A., et al.: W2v-BERT: combining contrastive learning and masked language modeling for self-supervised speech pre-training. In: 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 244\u2013250 (2021)","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"4_CR11","unstructured":"Barrault, L., et al.: Seamless: Multilingual Expressive and Streaming Speech Translation. arXiv preprint arXiv:2312.05187 (2023)"},{"key":"4_CR12","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: Proceedings of the 40th International Conference on Machine Learning 2022 (ICML 2023), pp. 28492\u201328518 (2023)"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Williams, A., Demarco, A., Borg, C.: The applicability of Wav2Vec 2.0 and Whisper for low-resource Maltese ASR. In: Proceedings of the 2nd Annual Meeting of the ELRA\/ISCA SIG on Under-resourced Languages (SIGUL 2023), pp. 39\u201343 (2023)","DOI":"10.21437\/SIGUL.2023-9"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Kozhirbayev, Z.: Kazakh Speech Recognition: wav2vec2. 0 vs. Whisper. J. Adv. Inf. Technol. 14(6), 1382\u20131389 (2023)","DOI":"10.12720\/jait.14.6.1382-1389"},{"key":"4_CR15","unstructured":"Gandhi, S., Platen, von, P., Rush, A.M.: Distil-Whisper: Robust knowledge distillation via large-scale pseudo labelling. arXiv preprint arXiv:2311.00430 (2023)."},{"key":"4_CR16","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1186\/s13636-024-00349-3","volume":"2024","author":"Y Liu","year":"2024","unstructured":"Liu, Y., Yang, X., Qu, D.: Exploration of Whisper fine-tuning strategies for low-resource ASR. EURASIP J. Audio, Speech Music Process. 2024, 29 (2024). https:\/\/doi.org\/10.1186\/s13636-024-00349-3","journal-title":"EURASIP J. Audio, Speech Music Process."},{"key":"4_CR17","doi-asserted-by":"publisher","unstructured":"Hiovain-Asikainen, K., De la Rosa, J.: Developing TTS and ASR for Lule and North S\u00e1mi languages. In: Proceedings of the 2nd Annual Meeting of the ELRA\/ISCA SIG on Under-resourced Languages (SIGUL 2023), pp. 48\u201352 (2023) https:\/\/doi.org\/10.21437\/SIGUL.2023-11","DOI":"10.21437\/SIGUL.2023-11"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Heller, M.: Codeswitching: Anthropological and Sociolinguistic Perspectives. De Gruyter Mouton, Berlin \u2013 New York (1988)","DOI":"10.1515\/9783110849615"},{"issue":"1","key":"4_CR19","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1111\/j.0079-1636.2004.00131.x","volume":"102","author":"P Gardner-Chloros","year":"2004","unstructured":"Gardner-Chloros, P., Edwards, M.: Assumptions behind grammatical approaches to code-switching: when the blueprint is a red herring. Trans. Philol. Soc. 102(1), 103\u2013129 (2004)","journal-title":"Trans. Philol. Soc."},{"key":"4_CR20","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198240594.001.0001","volume-title":"Duelling languages","author":"C Myers-Scotton","year":"1993","unstructured":"Myers-Scotton, C.: Duelling languages. Grammatical structure in code-switching. Clarendon Press, Oxford (1993)"},{"key":"4_CR21","volume-title":"Syntactic transfer, contact-induced change, and the evolution of bilingual mixed codes: Focus on Karelian-Russian language alternation","author":"A Sarhimaa","year":"1999","unstructured":"Sarhimaa, A.: Syntactic transfer, contact-induced change, and the evolution of bilingual mixed codes: Focus on Karelian-Russian language alternation. Finnish Literature Society, Helsinki (1999)"},{"key":"4_CR22","unstructured":"Povey, D., et al.: The Kaldi speech recognition toolkit. In: Proceedings of the ASRU 2011 \u2013 2011 IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 1\u20134. Waikoloa, HI, USA (2011)"},{"key":"4_CR23","doi-asserted-by":"publisher","unstructured":"Kipyatkova I., Kagirov I.: Deep models for low-resourced speech recognition: Livvi-Karelian case. Mathematics 11(18), ID 3814 (2023) https:\/\/doi.org\/10.3390\/math11183814","DOI":"10.3390\/math11183814"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Povey, D., et al.: Semi-orthogonal low-rank matrix factorization for deep neural networks. In: Proceedings of the INTERSPEECH 2018 \u2013 19th Annual Conference of the International Speech Communication Association, pp. 3743\u20133747. Hyderabad, India (2018)","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Saon, G., Soltau, H., Nahamoo, D., Picheny, M.: Speaker adaptation of neural network acoustic models using i-Vectors. In: Proceedings of the ASRU 2013 \u2013 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 55\u201359. Olomouc, Czech Republic, (2013)","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Kipyatkova, I., Kagirov, I.: Phone durations modeling for Livvi-Karelian ASR. In: Proceedings of the 25th International Conference SPECOM 2023, Springer, Lecture Notes in Computer Science, vol. 14339, pp. 87\u201399. Dharwad, India (2023)","DOI":"10.1007\/978-3-031-48312-7_7"},{"key":"4_CR27","unstructured":"Stolcke, A., Zheng, J., Wang, W., Abrash, V.: SRILM at sixteen: update and outlook. In: Proceedings of ASRU 2011 \u2013 2011 IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 5\u20139. Waikoloa, HI, USA (2011)"},{"key":"4_CR28","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/j.specom.2013.07.004","volume":"56","author":"A Karpov","year":"2014","unstructured":"Karpov, A., Markov, K., Kipyatkova, I., Vazhenina, D., Ronzhin, A.: Large vocabulary Russian speech recognition using syntactico-statistical language modeling. Speech Commun. 56, 213\u2013228 (2014). https:\/\/doi.org\/10.1016\/j.specom.2013.07.004","journal-title":"Speech Commun."},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Enarvi, S., Kurimo, M.: TheanoLM \u2013 an extensible toolkit for neural network language modeling. In: Proceedings of INTERSPEECH 2016 \u2013 17th Annual Conference of the International Speech Communication Association, pp. 3052\u20133056. San Francisco, CA, USA (2016)","DOI":"10.21437\/Interspeech.2016-618"},{"key":"4_CR30","unstructured":"Wolf, T., et al.: Huggingface\u2019s transformers: State-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019)"},{"key":"4_CR31","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 (Vol. 1: Long Papers), pp. 993\u20131003 (2021)","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Gulati, A., et al.: Conformer: Convolution-augmented transformer for speech recognition. arXiv preprint arXiv:2005.08100 (2020)","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Ogunremi, T., Manning, C.D., Jurafsky, D.: Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching. arXiv preprint arXiv:2311.15077 (2023)","DOI":"10.18653\/v1\/2023.calcs-1.8"},{"key":"4_CR34","doi-asserted-by":"publisher","unstructured":"Grosz, T., Getman, Y., Al-Ghezi, R., Rouhe, A., Kurimo, M.: Investigating wav2vec2 context representations and the effects of fine-tuning, a case-study of a Finnish model. In: Proceedings of INTERSPEECH 2023, pp. 196\u2013200 (2023) https:\/\/doi.org\/10.21437\/Interspeech.2023-837","DOI":"10.21437\/Interspeech.2023-837"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Bisani M., Ney, H.: Bootstrap estimates for confidence intervals in ASR performance evaluation. In: Proceedings of ICASSP 2004 \u2013 2044 IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. I\u2013409. Montreal, Canada (2004)","DOI":"10.1109\/ICASSP.2004.1326009"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-77961-9_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T16:02:35Z","timestamp":1736438555000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-77961-9_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031779602","9783031779619"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-77961-9_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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":"Belgrade","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Serbia","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":"25 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2024","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":"specom2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/specom2024.ftn.uns.ac.rs\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}