{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T22:20:20Z","timestamp":1766269220991},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030313715"},{"type":"electronic","value":"9783030313722"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-31372-2_4","type":"book-chapter","created":{"date-parts":[[2019,9,27]],"date-time":"2019-09-27T00:02:49Z","timestamp":1569542569000},"page":"44-55","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Recent Advances in End-to-End Spoken Language Understanding"],"prefix":"10.1007","author":[{"given":"Natalia","family":"Tomashenko","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antoine","family":"Caubri\u00e8re","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yannick","family":"Est\u00e8ve","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antoine","family":"Laurent","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emmanuel","family":"Morin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,9,27]]},"reference":[{"key":"4_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":"4_CR2","doi-asserted-by":"crossref","unstructured":"Bahdanau, D., Chorowski, J., Serdyuk, D., Brakel, P., Bengio, Y.: End-to-end attention-based large vocabulary speech recognition. In: ICASSP, pp. 4945\u20134949. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"4_CR3","unstructured":"Bechet, F., Maza, B., Bigouroux, N., Bazillon, T., El-Beze, M., et al.: DECODA: a call-centre human-human spoken conversation corpus. In: LREC, pp. 1343\u20131347 (2012)"},{"key":"4_CR4","unstructured":"Bonneau-Maynard, H., Ayache, C., Bechet, F., et al.: Results of the French Evalda-Media evaluation campaign for literal understanding. In: LREC (2006)"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y.P., Price, R., Bangalore, S.: Spoken language understanding without speech recognition. In: ICASSP (2018)","DOI":"10.1109\/ICASSP.2018.8461718"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Deena, S., et al.: Semi-supervised adaptation of RNNLMs by fine-tuning with domain-specific auxiliary features. In: INTERSPEECH, pp. 2715\u20132719. ISCA (2017)","DOI":"10.21437\/Interspeech.2017-1598"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Delcroix, M., Watanabe, S., Ogawa, A., Karita, S., Nakatani, T.: Auxiliary feature based adaptation of end-to-end ASR systems. In: INTERSPEECH, pp. 2444\u20132448 (2018)","DOI":"10.21437\/Interspeech.2018-1438"},{"key":"4_CR8","unstructured":"Devillers, L., et al.: The French MEDIA\/EVALDA project: the evaluation of the understanding capability of spoken language dialogue systems. In: LREC (2004)"},{"key":"4_CR9","unstructured":"Est\u00e8ve, Y., Bazillon, T., Antoine, J.Y., B\u00e9chet, F., Farinas, J.: The EPAC corpus: manual and automatic annotations of conversational speech in French broadcast news. In: LREC (2010)"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Galliano, S., et al.: The ESTER 2 evaluation campaign for the rich transcription of French radio broadcasts. In: Interspeech (2009)","DOI":"10.21437\/Interspeech.2009-680"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Ghannay, S., Caubri\u00e8re, A., Est\u00e8ve, Y., et al.: End-to-end named entity and semantic concept extraction from speech. In: SLT, pp. 692\u2013699 (2018)","DOI":"10.1109\/SLT.2018.8639513"},{"key":"4_CR12","unstructured":"Giraudel, A., Carr\u00e9, M., Mapelli, V., Kahn, J., Galibert, O., Quintard, L.: The REPERE corpus: a multimodal corpus for person recognition. In: LREC, pp. 1102\u20131107 (2012)"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Graves, A., et al.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369\u2013376. ACM (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"4_CR14","unstructured":"Gravier, G., Adda, G., Paulson, N., et al.: The ETAPE corpus for the evaluation of speech-based TV content processing in the French language. In: LREC (2012)"},{"key":"4_CR15","unstructured":"Grouin, C., Rosset, S., Zweigenbaum, P., Fort, K., Galibert, O., Quintard, L.: Proposal for an extension of traditional named entities: from guidelines to evaluation, an overview. In: Proceedings of the 5th Linguistic Annotation Workshop, pp. 92\u2013100 (2011)"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Haghani, P., et al.: From audio to semantics: approaches to end-to-end spoken language understanding. arXiv preprint arXiv:1809.09190 (2018)","DOI":"10.1109\/SLT.2018.8639043"},{"key":"4_CR17","unstructured":"Lef\u00e8vre, F., et al.: Robustness and portability of spoken language understanding systems among languages and domains: the PortMedia project (in French), pp. 779\u2013786 (2012)"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Lugosch, L., Ravanelli, M., Ignoto, P., Tomar, V.S., Bengio, Y.: Speech model pre-training for end-to-end spoken language understanding. arXiv preprint arXiv:1904.03670 (2019)","DOI":"10.21437\/Interspeech.2019-2396"},{"issue":"10","key":"4_CR19","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2010","unstructured":"Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345\u20131359 (2010)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"4_CR20","unstructured":"Povey, D., Ghoshal, A., et al.: The Kaldi speech recognition toolkit. In: ASRU (2011)"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Qian, Y., Ubale, R., et al.: Exploring ASR-free end-to-end modeling to improve spoken language understanding in a cloud-based dialog system. In: ASRU, pp. 569\u2013576 (2017)","DOI":"10.1109\/ASRU.2017.8268987"},{"key":"4_CR22","unstructured":"Rousseau, A., Del\u00e9glise, P., Esteve, Y.: Enhancing the TED-LIUM corpus with selected data for language modeling and more ted talks. In: LREC, pp. 3935\u20133939 (2014)"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Saon, G., Soltau, H., Nahamoo, D., Picheny, M.: Speaker adaptation of neural network acoustic models using i-vectors. In: ASRU, pp. 55\u201359 (2013)","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Serdyuk, D., Wang, Y., Fuegen, C., Kumar, A., Liu, B., Bengio, Y.: Towards end-to-end spoken language understanding. arXiv preprint arXiv:1802.08395 (2018)","DOI":"10.1109\/ICASSP.2018.8461785"},{"key":"4_CR25","unstructured":"Simonnet, E., et al.: Simulating ASR errors for training SLU systems. In: LREC 2018 (2018)"},{"key":"4_CR26","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104\u20133112 (2014)"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Tomashenko, N., Caubri\u00e8re, A., Est\u00e8ve, Y.: Investigating adaptation and transfer learning for end-to-end spoken language understanding from speech. In: Interspeech, Graz, Austria (2019)","DOI":"10.21437\/Interspeech.2019-2158"},{"key":"4_CR28","unstructured":"Tomashenko, N., Est\u00e8ve, Y.: Evaluation of feature-space speaker adaptation for end-to-end acoustic models. In: LREC (2018)"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Vukotic, V., Raymond, C., Gravier, G.: Is it time to switch to word embedding and recurrent neural networks for spoken language understanding? In: Interspeech (2015)","DOI":"10.21437\/Interspeech.2015-41"}],"container-title":["Lecture Notes in Computer Science","Statistical Language and Speech Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-31372-2_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T01:28:16Z","timestamp":1664501296000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-31372-2_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030313715","9783030313722"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-31372-2_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"27 September 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SLSP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Statistical Language and Speech Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ljubljana","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovenia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"slsp2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/slsp2019.irdta.eu\/","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":"48","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":"25","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":"1","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":"52% - 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)"}}]}}