{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T14:37:25Z","timestamp":1726238245505},"publisher-location":"Cham","reference-count":26,"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_6","type":"book-chapter","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T15:03:21Z","timestamp":1700579001000},"page":"68-76","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Emotional Speech Recognition of Holocaust Survivors with Deep Neural Network Models for Russian Language"],"prefix":"10.1007","author":[{"ORCID":"http:\/\/orcid.org\/0009-0000-7654-9612","authenticated-orcid":false,"given":"Liudmila","family":"Bukreeva","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0009-0005-1753-9904","authenticated-orcid":false,"given":"Daria","family":"Guseva","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-4344-2330","authenticated-orcid":false,"given":"Mikhail","family":"Dolgushin","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0001-9742-5299","authenticated-orcid":false,"given":"Vera","family":"Evdokimova","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-1045-575X","authenticated-orcid":false,"given":"Vasilisa","family":"Obotnina","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"key":"6_CR1","unstructured":"Project MALACH \u2013 Multilingual Access to Large Spoken Archives. https:\/\/malach.umiacs.umd.edu\/"},{"key":"6_CR2","unstructured":"USC Shoah Foundation. https:\/\/sfi.usc.edu\/"},{"key":"6_CR3","unstructured":"Word Error Rate. https:\/\/en.wikipedia.org\/wiki\/Word_error_rate"},{"key":"6_CR4","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.21437\/Interspeech.2005-489","DOI":"10.21437\/Interspeech.2005-489"},{"key":"6_CR5","doi-asserted-by":"publisher","unstructured":"Ramabhadran, B., et al.: USC-SFI MALACH interviews and transcripts english. In: LDC2012S05. Web Download. Philadelphia: Linguistic Data Consortium (2012). https:\/\/doi.org\/10.35111\/7zfn-a492","DOI":"10.35111\/7zfn-a492"},{"key":"6_CR6","doi-asserted-by":"publisher","unstructured":"Psutka, J., Radov\u00e1, V., Ircing, P., Matou\u0161ek, J., M\u00fcller, L.: USC-SFI MALACH interviews and transcripts Czech. In: LDC2014S04. Web Download. Philadelphia: Linguistic Data Consortium (2014). https:\/\/doi.org\/10.35111\/v2nt-7j09","DOI":"10.35111\/v2nt-7j09"},{"key":"6_CR7","doi-asserted-by":"publisher","unstructured":"Picheny, M., T\u00fcske, Z., Kingsbury, B., Audhkhasi, K., Cui, X., Saon, G.: Challenging the boundaries of speech recognition: the MALACH corpus. In: Interspeech 2019, pp. 326\u2013330 (2019). https:\/\/doi.org\/10.21437\/Interspeech.2019-1907","DOI":"10.21437\/Interspeech.2019-1907"},{"key":"6_CR8","doi-asserted-by":"publisher","unstructured":"Psutka, J.V., Pra\u017e\u00e1k, A., Van\u011bk, J.: Recognition of heavily accented and emotional speech of english and czech holocaust survivors using various DNN Architectures. In: Karpov, A., Potapova, R. (eds) Speech and Computer. SPECOM 2021. Lecture Notes in Computer Science(), vol 12997, pp. 553\u2013564. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87802-3_50","DOI":"10.1007\/978-3-030-87802-3_50"},{"key":"6_CR9","unstructured":"Svetozarova, N., Kleiner, Y., De Graaf, T., Nieuweboer, R.: Russian-Yiddish: Phonetic aspects of language interference. In: Proc. of the XIV International Congress of Phonetic Sciences. San-Francisco, pp. 1397\u20131400 (1999). https:\/\/www.internationalphoneticassociation.org\/icphs-proceedings\/ICPhS1999\/papers\/p14_1397.pdf"},{"key":"6_CR10","unstructured":"Weinreich, U.: Notes on the Yiddish Rise-Fall Intonation Contour. In: Columbia University (1956)"},{"key":"6_CR11","doi-asserted-by":"publisher","unstructured":"Lehe\u010dka, J., \u0160vec, J., Prazak, A., Psutka, J.: Exploring capabilities of monolingual audio transformers using large datasets in automatic speech recognition of Czech. In: Interspeech 2022, 1831\u20131835 (2022). https:\/\/doi.org\/10.21437\/Interspeech.2022-10439","DOI":"10.21437\/Interspeech.2022-10439"},{"key":"6_CR12","doi-asserted-by":"publisher","unstructured":"Li, J.: Recent Advances in End-to-End Automatic Speech Recognition. In: APSIPA Transactions on Signal and Information Processing 11(1) (2021). https:\/\/doi.org\/10.48550\/arXiv.2111.01690","DOI":"10.48550\/arXiv.2111.01690"},{"key":"6_CR13","doi-asserted-by":"publisher","unstructured":"Baevski, A., Zhou, H., Mohamed, A., Auli, M.: wav2vec 2.0: A framework for self-supervised learning of speech representation. In: Proceedings of the 34th International Conference on Neural Information Processing Systems, pp. 12449\u201312460 (2020). https:\/\/doi.org\/10.48550\/arXiv.2006.11477","DOI":"10.48550\/arXiv.2006.11477"},{"key":"6_CR14","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.48550\/arXiv.1912.06670","DOI":"10.48550\/arXiv.1912.06670"},{"key":"6_CR15","doi-asserted-by":"publisher","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, Online. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.80","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"6_CR16","unstructured":"USC Shoah Foundation Visual History Archive Online. https:\/\/vhaonline.usc.edu\/quickSearch\/resultList"},{"key":"6_CR17","unstructured":"YouTube playlist of Holocaust survivors testimonies by Yad Vashem foundation. https:\/\/www.youtube.com\/playlist?list=PLanQ0TFmIYBTV8sRAkSDWQLZNhbM-v1xp"},{"key":"6_CR18","doi-asserted-by":"publisher","unstructured":"Karpov, N., Denisenko, A., Minkin, F.: Golos: Russian Dataset for Speech Research. arXiv preprint (2021) https:\/\/doi.org\/10.48550\/arXiv.2106.10161","DOI":"10.48550\/arXiv.2106.10161"},{"key":"6_CR19","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","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"6_CR20","unstructured":"Bondarko, L., et al.: Phonetic properties of Russian spontaneous speech. In: Proceedings of the 15th International Congress of Phonetic Sciences, Barcelona, pp. 2973\u20132976 (2003). https:\/\/www.internationalphoneticassociation.org\/icphs-proceedings\/ICPhS2003\/p15_2973.html"},{"key":"6_CR21","doi-asserted-by":"publisher","unstructured":"Lehe\u010dka, J., Psutka, J.V., Psutka, J.: Transformer-based automatic speech recognition of formal and colloquial Czech in MALACH Project. In: Sojka, P., Hor\u00e1k, A., Kope\u010dek, I., Pala, K. (eds) Text, Speech, and Dialogue. TSD 2022. Lecture Notes in Computer Science(), vol 13502, pp. 301\u2013312. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-16270-1_25","DOI":"10.1007\/978-3-031-16270-1_25"},{"key":"6_CR22","unstructured":"Barseghyan, A.: Transliterate Module Documentation. https:\/\/pypi.org\/project\/transliterate"},{"key":"6_CR23","unstructured":"Num2words Module Documentation. https:\/\/pypi.org\/project\/num2words\/"},{"key":"6_CR24","unstructured":"Grosman, J.: Fine-tuned XLS-R 1B model for speech recognition in Russian. https:\/\/huggingface.co\/jonatasgrosman\/wav2vec2-xls-r-1b-russian"},{"key":"6_CR25","doi-asserted-by":"publisher","unstructured":"Salesky, E., et al.: The multilingual tedx corpus for speech recognition and translation. In: Proc. Interspeech 2021, pp. 3655\u20133659 (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-11","DOI":"10.21437\/Interspeech.2021-11"},{"key":"6_CR26","unstructured":"RuOH dataset on HuggingFacet. https:\/\/huggingface.co\/datasets\/Mihaj\/ruoh_demo"}],"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_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T15:10:28Z","timestamp":1700579428000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-48309-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031483080","9783031483097"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-48309-7_6","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)"}}]}}