{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T14:41:13Z","timestamp":1762094473484,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031483080"},{"type":"electronic","value":"9783031483097"}],"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\/978-3-031-48309-7_4","type":"book-chapter","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:03:21Z","timestamp":1700597001000},"page":"43-56","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Everyday Conversations: A Comparative Study of Expert Transcriptions and ASR Outputs at a Lexical Level"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9085-3378","authenticated-orcid":false,"given":"Tatiana","family":"Sherstinova","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3362-3290","authenticated-orcid":false,"given":"Rostislav","family":"Kolobov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5660-0601","authenticated-orcid":false,"given":"Nikolay","family":"Mikhaylovskiy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Ali, A., Renals, S.: Word error rate estimation for speech recognition: e-WER. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Vol. 2: Short Papers. Melbourne, Australia. Association for Computational Linguistics, pp. 20\u201324 (2018). https:\/\/aclanthology.org\/P18-2004.pdf","DOI":"10.18653\/v1\/P18-2004"},{"key":"4_CR2","unstructured":"AntConc. http:\/\/www.laurenceanthony.net\/software.html. Accessed 1 Sept 2023"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Asinovsky, A., Bogdanova, N., Rusakova, M., Stepanova, S., Ryko, A., Sherstinova, S.: The ORD speech corpus of Russian everyday communication \u201cOne Speaker\u2019s Day\u201d: creation principles and annotation. In: Matou\u0161ek, V., Mautner, P. (eds) Text, Speech and Dialogue. TSD 2009. Lecture Notes in Computer Science, vol 5729, pp. 250\u2013257. Springer, Berlin, Heidelberg (2009)","DOI":"10.1007\/978-3-642-04208-9_36"},{"key":"4_CR4","unstructured":"Bakhturina, E., Lavrukhin, V., Ginsburg, B.: A toolbox for construction and analysis of speech datasets. Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks, 1 (2021)"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Bogdanova-Beglarian, N., Sherstinova, T., Blinova, O., Ermolova, O., Baeva, E., Martynenko, G., Ryko, A.: Sociolinguistic extension of the ORD corpus of Russian everyday speech. Ronzhin, A., et al. (eds.),\u00a0SPECOM 2016,\u00a0Lecture Notes in Artificial Intelligence, LNAI, 9811, pp. 659\u2013666. Springer, Switzerland (2016)","DOI":"10.1007\/978-3-319-43958-7_80"},{"key":"4_CR6","first-page":"183","volume":"2004","author":"N Campbell","year":"2004","unstructured":"Campbell, N.: Speech & expression; the value of a longitudinal corpus. LREC 2004, 183\u2013186 (2004)","journal-title":"LREC"},{"key":"4_CR7","unstructured":"Child, R., Gray, S., Radford, A., Sutskever, I.: Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509 (2019)"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Gulati, A., et al.: Conformer: convolution-augmented transformer for speech recognition. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, pp. 5036\u20135040 (2020)","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"4_CR9","unstructured":"Hellwig, B., Van Uytvanck, D., Hulsbosch, M., et al.: ELAN \u2014 Linguistic Annotator. Version 4.9.3 [in:] http:\/\/tla.mpi.nl\/tools\/tla-tools\/elan\/ Linguistic Annotator ELAN. https:\/\/tla.mpi.nl\/tools\/tla-tools\/elan\/"},{"key":"4_CR10","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian Error Linear Units (gelus). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"4_CR11","unstructured":"https:\/\/catalog.ngc.nvidia.com\/orgs\/nvidia\/teams\/nemo\/models\/stt_ru_conformer_ctc_large"},{"key":"4_CR12","unstructured":"https:\/\/github.com\/sovaai\/sova-dataset"},{"key":"4_CR13","unstructured":"https:\/\/voice.mozilla.org"},{"key":"4_CR14","doi-asserted-by":"publisher","unstructured":"Karpov, N., Denisenko, A., Minkin, F.: Golos: Russian dataset for speech research. Proc. Annu. Conf. Int. Speech Commun. Assoc. INTERSPEECH 2, 1076\u20131080 (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-462","DOI":"10.21437\/Interspeech.2021-462"},{"key":"4_CR15","unstructured":"Kolobov, R., et al.: Mediaspeech: Multilanguage ASR Benchmark and Dataset.\u00a0arXiv, arXiv:2103.16193 (2021)"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Morris, A.C., Maier, V., Green, P.: From WER and RIL to MER and WIL: improved evaluation measures for connected speech recognition. In: Eighth International Conference on Spoken Language Processing, pp. 2765\u20132768 (2004). https:\/\/www.isca-speech.org\/archive_v0\/archive_papers\/interspeech_2004\/i04_2765.pdf?ref=https:\/\/githubhelp.com","DOI":"10.21437\/Interspeech.2004-668"},{"key":"4_CR17","unstructured":"One Speech Day corpus online. https:\/\/ord.spbu.ru\/"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Press, O., Wolf, L.: Using the output embedding to improve language models. In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pp. 157\u2013163, Valencia, Spain, April 2017. Association for Computational Linguistics (2017)","DOI":"10.18653\/v1\/E17-2025"},{"key":"4_CR19","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202, 28492\u201328518 (2023)"},{"key":"4_CR20","unstructured":"Reference Guide for the British National Corpus. http:\/\/www.natcorp.ox.ac.uk\/docs\/URG.xml"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Sherstinova, T.: Macro episodes of Russian everyday oral communication: towards pragmatic annotation of the ORD speech corpus. Ronzhin, A., et al. (eds.) SPECOM 2015. Lecture Notes in Artificial Intelligence, LNAI. Vol. 9319. Springer, Switzerland, pp. 268\u2013276 (2015)","DOI":"10.1007\/978-3-319-23132-7_33"},{"key":"4_CR22","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1007\/978-3-642-04208-9_37","volume-title":"Text, Speech and Dialogue","author":"T Sherstinova","year":"2009","unstructured":"Sherstinova, T.: The structure of the ORD speech corpus of Russian everyday communication. In: Matou\u0161ek, V., Mautner, P. (eds.) TSD 2009. LNCS (LNAI), vol. 5729, pp. 258\u2013265. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-04208-9_37"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Von\u00a0Neumann, T., Boeddeker, C., Kinoshita, K., Delcroix, M., Haeb-Umbach, R.: On word error rate definitions and their efficient computation for multi-speaker speech recognition systems. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, pp. 1\u20135 (2023). https:\/\/ieeexplore.ieee.org\/abstract\/document\/10094784\/","DOI":"10.1109\/ICASSP49357.2023.10094784"},{"key":"4_CR24","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5999\u20136009 (2017)"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Bogdanova-Beglarian, N., Blinova, O., Sherstinova, T., Troshchenkova, E.: Russian pragmatic markers database: developing speech technologies for everyday spoken discourse. In: 26th Conference of Open Innovations Association FRUCT, FRUCT 2020; Yaroslavl; Russian Federation, pp. 60\u201366 (2020)","DOI":"10.23919\/FRUCT48808.2020.9087473"},{"key":"4_CR26","unstructured":"Bogdanova-Beglarian, N., Sherstinova, T., Kisloshchuk, A.: On the rhythm-forming function of discursive units. Perm University Herald. Russian and Foreign Philology 2(22), 7\u201317 (2013)"},{"key":"4_CR27","unstructured":"Holtzman, A., et al.: The curious case of neural text degeneration. In: Proceedings of the 2020 International Conference on Learning Representations, p. 2540 (2020)"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-48309-7_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:09:53Z","timestamp":1700597393000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-48309-7_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031483080","9783031483097"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-48309-7_4","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":"22 November 2023","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":"Dharwad","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"29 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iitdh.ac.in\/specom-2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"174","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":"94","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":"54% - 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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}