{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:19:10Z","timestamp":1757312350403,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"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_10","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T13:54:23Z","timestamp":1732197263000},"page":"137-150","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["The ParlaSpeech Collection of\u00a0Automatically Generated Speech and\u00a0Text Datasets from\u00a0Parliamentary Proceedings"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7169-9152","authenticated-orcid":false,"given":"Nikola","family":"Ljube\u0161i\u0107","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9700-3686","authenticated-orcid":false,"given":"Peter","family":"Rupnik","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2916-4856","authenticated-orcid":false,"given":"Danijel","family":"Kor\u017einek","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"10_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"10_CR2","unstructured":"Ardila, R., et al.: Common voice: a massively-multilingual speech corpus. arXiv preprint arXiv:1912.06670 (2019)"},{"key":"10_CR3","unstructured":"Baevski, A., Hsu, W.N., Xu, Q., Babu, A., Gu, J., Auli, M.: Data2vec: a general framework for self-supervised learning in speech, vision and language. In: International Conference on Machine Learning, pp. 1298\u20131312. PMLR (2022)"},{"key":"10_CR4","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, 12449\u201312460 (2020)"},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Bakhturina, E., Zhang, Y., Ginsburg, B.: Shallow fusion of weighted finite-state transducer and language model for text normalization (2022). https:\/\/arxiv.org\/abs\/2203.15917","DOI":"10.21437\/Interspeech.2022-11074"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Bredin, H.: pyannote.audio 2.1 speaker diarization pipeline: principle, benchmark, and recipe. In: Proceedings of the INTERSPEECH 2023 (2023)","DOI":"10.21437\/Interspeech.2023-105"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Conneau, A., Baevski, A., Collobert, R., Mohamed, A., Auli, M.: Unsupervised cross-lingual representation learning for speech recognition (2020). https:\/\/arxiv.org\/abs\/2006.13979","DOI":"10.21437\/Interspeech.2021-329"},{"issue":"1","key":"10_CR8","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/s10579-021-09574-0","volume":"57","author":"T Erjavec","year":"2023","unstructured":"Erjavec, T., et al.: The parlamint corpora of parliamentary proceedings. Lang. Resour. Eval. 57(1), 415\u2013448 (2023)","journal-title":"Lang. Resour. Eval."},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Helgad\u00f3ttir, I.R., Kjaran, R., Nikul\u00e1sd\u00f3ttir, A.B., Gu$$\\eth $$nason, J.: Building an ASR corpus using althingi\u2019s parliamentary speeches. In: Interspeech, pp. 2163\u20132167 (2017)","DOI":"10.21437\/Interspeech.2017-903"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Imseng, D., Bourlard, H., Caesar, H., Garner, P.N., Lecorv\u00e9, G., Nanchen, A.: MediaParl: bilingual mixed language accented speech database. In: 2012 IEEE spoken language technology workshop (SLT), pp. 263\u2013268. IEEE (2012)","DOI":"10.1109\/SLT.2012.6424233"},{"key":"10_CR11","unstructured":"Katsamanis, A., Black, M., Georgiou, P.G., Goldstein, L., Narayanan, S.: SailAlign: robust long speech-text alignment. In: Proceedings of Workshop on New Tools and Methods for Very-Large Scale Phonetics Research, vol.\u00a01 (2011)"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Kirkedal, A., Stepanovi\u0107, M., Plank, B.: Ft Speech: danish parliament speech corpus. arXiv preprint arXiv:2005.12368 (2020)","DOI":"10.21437\/Interspeech.2020-3164"},{"key":"10_CR13","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/978-3-030-83527-9_25","volume-title":"Text, Speech, and Dialogue","author":"M Kopp","year":"2021","unstructured":"Kopp, M., Stankov, V., Kr\u016fza, J.O., Stra\u0148\u00e1k, P., Bojar, O.: ParCzech 3.0: a large czech speech corpus with rich metadata. In: Ek\u0161tein, K., P\u00e1rtl, F., Konop\u00edk, M. (eds.) TSD 2021. LNCS (LNAI), vol. 12848, pp. 293\u2013304. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-83527-9_25"},{"key":"10_CR14","unstructured":"Kratochv\u00edl, J., Pol\u00e1k, P., Bojar, O.: Large corpus of czech parliament plenary hearings. In: Proceedings of the Twelfth Language Resources and Evaluation Conference, pp. 6363\u20136367 (2020)"},{"key":"10_CR15","unstructured":"Ljube\u0161i\u0107, N., Kor\u017einek, D., Rupnik, P., Jazbec, I.P.: ParlaSpeech-HR-a freely available ASR dataset for croatian bootstrapped from the ParlaMint corpus. In: Proceedings of the workshop ParlaCLARIN III within the 13th language resources and evaluation Conference, pp. 111\u2013116 (2022)"},{"key":"10_CR16","doi-asserted-by":"publisher","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: Librispeech: An ASR corpus based on public domain audio books. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5206\u20135210 (2015). https:\/\/doi.org\/10.1109\/ICASSP.2015.7178964, https:\/\/ieeexplore.ieee.org\/document\/7178964","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"10_CR17","unstructured":"Pl\u00fcss, M., et\u00a0al.: SDS-200: A swiss German speech to standard German text corpus. arXiv preprint arXiv:2205.09501 (2022)"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Qi, P., Zhang, Y., Zhang, Y., Bolton, J., Manning, C.D.: Stanza: A Python natural language processing toolkit for many human languages. arXiv preprint arXiv:2003.07082 (2020)","DOI":"10.18653\/v1\/2020.acl-demos.14"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77, 257\u2013286 (1989). https:\/\/api.semanticscholar.org\/CorpusID:13618539","DOI":"10.1109\/5.18626"},{"key":"10_CR20","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning, pp. 28492\u201328518. PMLR (2023)"},{"issue":"4","key":"10_CR21","doi-asserted-by":"publisher","first-page":"2761","DOI":"10.1007\/s11831-023-09884-2","volume":"30","author":"V Rani","year":"2023","unstructured":"Rani, V., Nabi, S.T., Kumar, M., Mittal, A., Kumar, K.: Self-supervised learning: a succinct review. Arch. Comput. Methods Eng. 30(4), 2761\u20132775 (2023)","journal-title":"Arch. Comput. Methods Eng."},{"issue":"13s","key":"10_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3577925","volume":"55","author":"MC Schiappa","year":"2023","unstructured":"Schiappa, M.C., Rawat, Y.S., Shah, M.: Self-supervised learning for videos: a survey. ACM Comput. Surv. 55(13s), 1\u201337 (2023)","journal-title":"ACM Comput. Surv."},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Schmidt, T., W\u00f6rner, K.: EXMARaLDA (2014)","DOI":"10.1093\/oxfordhb\/9780199571932.013.030"},{"key":"10_CR24","unstructured":"Solberg, P.E., Ortiz, P.: The norwegian parliamentary speech corpus. arXiv preprint arXiv:2201.10881 (2022)"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Stolcke, A., et\u00a0al.: SRILM-an extensible language modeling toolkit. In: Interspeech, vol.\u00a02002, p.\u00a02002 (2002)","DOI":"10.21437\/ICSLP.2002-303"},{"key":"10_CR26","unstructured":"Styler, W.: Using praat for linguistic research. University of Colorado at Boulder Phonetics Lab (2013)"},{"key":"10_CR27","unstructured":"Ter\u010don, L., Ljube\u0161i\u0107, N.: Classla-stanza: the next step for linguistic processing of south slavic languages. arXiv preprint arXiv:2308.04255 (2023)"},{"issue":"4","key":"10_CR28","doi-asserted-by":"publisher","first-page":"1645","DOI":"10.1007\/s10579-023-09650-7","volume":"57","author":"A Virkkunen","year":"2023","unstructured":"Virkkunen, A., Rouhe, A., Phan, N., Kurimo, M.: Finnish parliament ASR corpus: analysis, benchmarks and statistics. Lang. Resour. Eval. 57(4), 1645\u20131670 (2023)","journal-title":"Lang. Resour. Eval."}],"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_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T16:05:32Z","timestamp":1736438732000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-77961-9_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031779602","9783031779619"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-77961-9_10","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":"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"}}]}}