{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T04:02:07Z","timestamp":1729569727966,"version":"3.28.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031340192"},{"type":"electronic","value":"9783031340208"}],"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\/978-3-031-34020-8_30","type":"book-chapter","created":{"date-parts":[[2023,5,26]],"date-time":"2023-05-26T10:02:30Z","timestamp":1685095350000},"page":"393-402","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automatic Generation of Subtitles for Videos of the Government of La Rioja"],"prefix":"10.1007","author":[{"given":"Mirari San","family":"Mart\u00edn","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-4775-1306","authenticated-orcid":false,"given":"J\u00f3nathan","family":"Heras","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-5567-8463","authenticated-orcid":false,"given":"Gadea","family":"Mata","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,5,27]]},"reference":[{"key":"30_CR1","unstructured":"Ardila, R., et al.: Common voice: a massively-multilingual speech corpus. arXiv preprint arXiv:1912.06670 (2019)"},{"key":"30_CR2","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":"30_CR3","unstructured":"Chan, W., Jaitly, N., Le, Q.V., Vinyals, O.: Listen, attend and spell. arXiv preprint arXiv:1508.01211 (2015)"},{"key":"30_CR4","unstructured":"de Espa\u00f1a, C.G.: Ley 34\/2002, de 11 de julio, de servicios de la sociedad de la informaci\u00f3n y de comercio electr\u00f3nico. No 166 12 (2002)"},{"key":"30_CR5","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":"30_CR6","unstructured":"Hannun, A., et al.: Deep speech: scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014)"},{"key":"30_CR7","unstructured":"Hernandez Mena, C.D.: Acoustic model in spanish: stt_es_quartznet15x5_ft_ep53_944h. (2022). https:\/\/huggingface.co\/carlosdanielhernandezmena\/stt_es_quartznet15x5_ft_ep53_944h"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Hong, R., et al.: Video accessibility enhancement for hearing-impaired users. ACM Trans. Multimed. Comput. Commun. Appl. (TOMM) 7(1), 1\u201319 (2011)","DOI":"10.1145\/2037676.2037681"},{"key":"30_CR9","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":"30_CR10","unstructured":"Hugging Face: Hugging Face Hub (2022). https:\/\/huggingface.co\/docs\/hub\/index"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Huggins-Daines, D., Kumar, M., Chan, A., Black, A.W., Ravishankar, M., Rudnicky, A.I.: Pocketsphinx: a free, real-time continuous speech recognition system for hand-held devices. In: 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings, vol. 1, p. I. IEEE (2006)","DOI":"10.1109\/ICASSP.2006.1659988"},{"key":"30_CR12","unstructured":"Jurafsky, D., Martin, J.H.: Speech and language processing (3rd draft ed.), 2019 (2022)"},{"key":"30_CR13","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":"30_CR14","unstructured":"Levenshtein, V.I., et al.: Binary codes capable of correcting deletions, insertions, and reversals. In: Soviet physics doklady, vol. 10, pp. 707\u2013710. Soviet Union (1966)"},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Jasper: an end-to-end convolutional neural acoustic model. arXiv preprint arXiv:1904.03288 (2019)","DOI":"10.21437\/Interspeech.2019-1819"},{"key":"30_CR16","doi-asserted-by":"publisher","first-page":"9411","DOI":"10.1007\/s11042-020-10073-7","volume":"80","author":"M Malik","year":"2021","unstructured":"Malik, M., Malik, M.K., Mehmood, K., Makhdoom, I.: Automatic speech recognition: a survey. Multimed. Tools Appl. 80, 9411\u20139457 (2021)","journal-title":"Multimed. Tools Appl."},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Pratap, V., Xu, Q., Sriram, A., Synnaeve, G., Collobert, R.: MLS: a large-scale multilingual dataset for speech research. arXiv preprint arXiv:2012.03411 (2020)","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"30_CR18","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. arXiv preprint arXiv:2212.04356 (2022)"},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"Sharif Razavian, A., Azizpour, H., Sullivan, J., Carlsson, S.: CNN features off-the-shelf: an astounding baseline for recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 806\u2013813 (2014)","DOI":"10.1109\/CVPRW.2014.131"},{"key":"30_CR20","unstructured":"Woodard, J., Nelson, J.: An information theoretic measure of speech recognition performance. In: Workshop on Standardisation for Speech I\/O Technology, Naval Air Development Center, Warminster, PA (1982)"},{"issue":"1","key":"30_CR21","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","volume":"109","author":"F Zhuang","year":"2020","unstructured":"Zhuang, F., et al.: A comprehensive survey on transfer learning. Proc. IEEE 109(1), 43\u201376 (2020)","journal-title":"Proc. IEEE"}],"container-title":["Communications in Computer and Information Science","Optimization and Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-34020-8_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T04:57:02Z","timestamp":1729486622000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-34020-8_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031340192","9783031340208"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-34020-8_30","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":"27 May 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"OLA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Optimization and Learning","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malaga","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","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":"3 May 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 May 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ola2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ola2023.sciencesconf.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Open","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"sciencesconf.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"78","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":"32","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":"41% - 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":"3","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)"}}]}}