{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T10:47:56Z","timestamp":1753181276305,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030835262"},{"type":"electronic","value":"9783030835279"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-83527-9_40","type":"book-chapter","created":{"date-parts":[[2021,8,29]],"date-time":"2021-08-29T23:04:59Z","timestamp":1630278299000},"page":"469-480","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Attention-Based End-to-End Named Entity Recognition from Speech"],"prefix":"10.1007","author":[{"given":"Dejan","family":"Porjazovski","sequence":"first","affiliation":[]},{"given":"Juho","family":"Leinonen","sequence":"additional","affiliation":[]},{"given":"Mikko","family":"Kurimo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,8,30]]},"reference":[{"key":"40_CR1","unstructured":"Amodei, D., et al.: Deep speech 2: end-to-end speech recognition in English and mandarin. In: International Conference on Machine Learning, pp. 173\u2013182 (2016)"},{"key":"40_CR2","first-page":"135","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski, P., Grave, E., Joulin, A., Mikolov, T.: Enriching word vectors with subword information. Trans. Assoc. Comput. Ling. 5, 135\u2013146 (2017)","journal-title":"Trans. Assoc. Comput. Ling."},{"key":"40_CR3","unstructured":"Chorowski, J.K., Bahdanau, D., Serdyuk, D., Cho, K., Bengio, Y.: Attention-based models for speech recognition. In: Advances in Neural Information Processing Systems, pp. 577\u2013585 (2015)"},{"key":"40_CR4","doi-asserted-by":"crossref","unstructured":"Deoras, A., Sarikaya, R.: Deep belief network based semantic taggers for spoken language understanding. In: Interspeech, pp. 2713\u20132717 (2013)","DOI":"10.21437\/Interspeech.2013-623"},{"key":"40_CR5","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":"40_CR6","doi-asserted-by":"crossref","unstructured":"Ghannay, S., et al.: End-to-end named entity and semantic concept extraction from speech. In: 2018 IEEE Spoken Language Technology Workshop (SLT), pp. 692\u2013699. IEEE (2018)","DOI":"10.1109\/SLT.2018.8639513"},{"key":"40_CR7","doi-asserted-by":"crossref","unstructured":"Gravano, A., Jansche, M., Bacchiani, M.: Restoring punctuation and capitalization in transcribed speech. In: 2009 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4741\u20134744. IEEE (2009)","DOI":"10.1109\/ICASSP.2009.4960690"},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"issue":"8","key":"40_CR9","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"40_CR10","doi-asserted-by":"crossref","unstructured":"Jeong, M., Lee, G.G.: Jointly predicting dialog act and named entity for spoken language understanding. In: 2006 IEEE Spoken Language Technology Workshop, pp. 66\u201369. IEEE (2006)","DOI":"10.1109\/SLT.2006.326818"},{"key":"40_CR11","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"40_CR12","unstructured":"Lafferty, J., McCallum, A., Pereira, F.C.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the 18th International Conference on Machine Learning 2001 (ICML 2001), pp. 282\u2013289 (2001)"},{"key":"40_CR13","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"40_CR14","unstructured":"Malmsten, M., B\u00f6rjeson, L., Haffenden, C.: Playing with words at the national library of Sweden - making a Swedish BERT (2020)"},{"key":"40_CR15","doi-asserted-by":"crossref","unstructured":"Mansikkaniemi, A., Smit, P., Kurimo, M., et al.: Automatic construction of the Finnish parliament speech corpus. In: INTERSPEECH, vol. 8, pp. 3762\u20133766 (2017)","DOI":"10.21437\/Interspeech.2017-1115"},{"key":"40_CR16","doi-asserted-by":"crossref","unstructured":"Mesnil, G., He, X., Deng, L., Bengio, Y.: Investigation of recurrent-neural-network architectures and learning methods for spoken language understanding. In: Interspeech, pp. 3771\u20133775 (2013)","DOI":"10.21437\/Interspeech.2013-596"},{"key":"40_CR17","doi-asserted-by":"crossref","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. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"40_CR18","doi-asserted-by":"crossref","unstructured":"Porjazovski, D., Leinonen, J., Kurimo, M.: Named entity recognition for spoken Finnish. In: Proceedings of the 2nd International Workshop on AI for Smart TV Content Production, Access and Delivery, pp. 25\u201329 (2020)","DOI":"10.1145\/3422839.3423066"},{"key":"40_CR19","unstructured":"Sang, E.F., De Meulder, F.: Introduction to the CoNLL-2003 shared task: language-independent named entity recognition. arXiv preprint cs\/0306050 (2003)"},{"key":"40_CR20","doi-asserted-by":"crossref","unstructured":"Toshniwal, S., Kannan, A., Chiu, C.C., Wu, Y., Sainath, T.N., Livescu, K.: A comparison of techniques for language model integration in encoder-decoder speech recognition. In: 2018 IEEE Spoken Language Technology Workshop (SLT), pp. 369\u2013375. IEEE (2018)","DOI":"10.1109\/SLT.2018.8639038"},{"issue":"8","key":"40_CR21","doi-asserted-by":"publisher","first-page":"1240","DOI":"10.1109\/JSTSP.2017.2763455","volume":"11","author":"S Watanabe","year":"2017","unstructured":"Watanabe, S., Hori, T., Kim, S., Hershey, J.R., Hayashi, T.: Hybrid CTC\/attention architecture for end-to-end speech recognition. IEEE J. Sel. Topics Sig. Process. 11(8), 1240\u20131253 (2017)","journal-title":"IEEE J. Sel. Topics Sig. Process."},{"key":"40_CR22","doi-asserted-by":"crossref","unstructured":"Yadav, H., Ghosh, S., Yu, Y., Shah, R.R.: End-to-end named entity recognition from English speech. arXiv preprint arXiv:2005.11184 (2020)","DOI":"10.21437\/Interspeech.2020-2482"},{"key":"40_CR23","doi-asserted-by":"crossref","unstructured":"Zhai, L., Fung, P., Schwartz, R., Carpuat, M., Wu, D.: Using N-best lists for named entity recognition from Chinese speech. In: Proceedings of HLT-NAACL 2004: Short Papers, pp. 37\u201340 (2004)","DOI":"10.3115\/1613984.1613994"}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-83527-9_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,29]],"date-time":"2021-08-29T23:16:49Z","timestamp":1630279009000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-83527-9_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030835262","9783030835279"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-83527-9_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"30 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TSD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Text, Speech, and Dialogue","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Olomouc","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.kiv.zcu.cz\/tsd2021\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"TSDEngine 3.2","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"101","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":"29","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":"17","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":"29% - 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":"2,93","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)"}}]}}