{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:43:52Z","timestamp":1760132632905,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030878016"},{"type":"electronic","value":"9783030878023"}],"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\/978-3-030-87802-3_19","type":"book-chapter","created":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T23:36:52Z","timestamp":1632267412000},"page":"202-213","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Where Are We in Semantic Concept Extraction for Spoken Language Understanding?"],"prefix":"10.1007","author":[{"given":"Sahar","family":"Ghannay","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antoine","family":"Caubri\u00e8re","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Salima","family":"Mdhaffar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ga\u00eblle","family":"Laperri\u00e8re","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bassam","family":"Jabaian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yannick","family":"Est\u00e8ve","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,22]]},"reference":[{"key":"19_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. PMLR (2016)"},{"key":"19_CR2","unstructured":"Baevski, A., Zhou, H., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. arXiv preprint arXiv:2006.11477 (2020)"},{"key":"19_CR3","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"B\u00e9chet, F., Raymond, C.: Benchmarking benchmarks: introducing new automatic indicators for benchmarking spoken language understanding corpora. In: Interspeech, Graz, Austria (2019)","DOI":"10.21437\/Interspeech.2019-3033"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Bonneau-Maynard, H., Rosset, S., Ayache, C., Kuhn, A., Mostefa, D.: Semantic annotation of the French media dialog corpus. In: INTERSPEECH (2005)","DOI":"10.21437\/Interspeech.2005-312"},{"key":"19_CR6","doi-asserted-by":"publisher","unstructured":"Caubri\u00e8re, A., Tomashenko, N., Laurent, A., Morin, E., Camelin, N., Est\u00e8ve, Y.: Curriculum-based transfer learning for an effective end-to-end spoken language understanding and domain portability. In: Proceedings Interspeech 2019, pp. 1198\u20131202 (2019). https:\/\/doi.org\/10.21437\/Interspeech.2019-1832","DOI":"10.21437\/Interspeech.2019-1832"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Chan, W., Jaitly, N., Le, Q., Vinyals, O.: Listen, attend and spell: a neural network for large vocabulary conversational speech recognition. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4960\u20134964. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Chiu, C.C., et al.: State-of-the-art speech recognition with sequence-to-sequence models. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4774\u20134778. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"19_CR9","unstructured":"Chorowski, J., Bahdanau, D., Cho, K., Bengio, Y.: End-to-end continuous speech recognition using attention-based recurrent NN: first results. arXiv preprint arXiv:1412.1602 (2014)"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Chung, Y.A., Zhu, C., Zeng, M.: SPLAT: speech-language joint pre-training for spoken language understanding. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1897\u20131907 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.152"},{"key":"19_CR11","unstructured":"Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., Kuksa, P.: Natural language processing (almost) from scratch. J. Mach. Learn. Res. 12, 2493\u20132537 (2011)"},{"key":"19_CR12","unstructured":"Coucke, A., et al.: Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces. arXiv preprint arXiv:1805.10190 (2018)"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Dahl, D.A., et al.: Expanding the scope of the ATIS task: The ATIS-3 corpus. In: Human Language Technology: Proceedings of a Workshop held at Plainsboro, New Jersey, 8\u201311 March 1994 (1994)","DOI":"10.3115\/1075812.1075823"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"De Mori, R.: Spoken language understanding: a survey. In: 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU), pp. 365\u2013376. IEEE (2007)","DOI":"10.1109\/ASRU.2007.4430139"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Desot, T., Portet, F., Vacher, M.: Towards end-to-end spoken intent recognition in smart home. In: 2019 International Conference on Speech Technology and Human-Computer Dialogue (SpeD), pp. 1\u20138. IEEE (2019)","DOI":"10.1109\/SPED.2019.8906584"},{"key":"19_CR16","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT. Association for Computational Linguistics, Minneapolis, Minnesota, June 2019. https:\/\/doi.org\/10.18653\/v1\/N19-1423. https:\/\/www.aclweb.org\/anthology\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Evain, S., et al.: Lebenchmark: a reproducible framework for assessing self-supervised representation learning from speech. In: Interspeech, Brno, Czechia (2021)","DOI":"10.21437\/Interspeech.2021-556"},{"key":"19_CR18","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":"19_CR19","doi-asserted-by":"publisher","unstructured":"Ghannay, S., Servan, C., Rosset, S.: Neural networks approaches focused on French spoken language understanding: application to the MEDIA evaluation task. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 2722\u20132727. International Committee on Computational Linguistics, Barcelona, Spain (Online), December 2020. https:\/\/doi.org\/10.18653\/v1\/2020.coling-main.245. https:\/\/www.aclweb.org\/anthology\/2020.coling-main.245","DOI":"10.18653\/v1\/2020.coling-main.245"},{"key":"19_CR20","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":"6","key":"19_CR21","doi-asserted-by":"publisher","first-page":"1569","DOI":"10.1109\/TASL.2010.2093520","volume":"19","author":"S Hahn","year":"2010","unstructured":"Hahn, S., et al.: Comparing stochastic approaches to spoken language understanding in multiple languages. IEEE Trans. Audio Speech Lang. Process. 19(6), 1569\u20131583 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"19_CR22","doi-asserted-by":"publisher","unstructured":"Hakkani-T\u00fc, D., B\u00e9chet, F., Riccardi, G., Tur, G.: Beyond ASR 1-best: using word confusion networks in spoken language understanding. Comput. Speech Lang. (2005). https:\/\/doi.org\/10.1016\/j.csl.2005.07.005. https:\/\/hal.archives-ouvertes.fr\/hal-01314993","DOI":"10.1016\/j.csl.2005.07.005"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Jabaian, B., Lef\u00e8vre, F.: Error-corrective discriminative joint decoding of automatic spoken language transcription and understanding. In: Bimbot, F., et al. (eds.) INTERSPEECH 2013, 14th Annual Conference of the International Speech Communication Association, Lyon, France, 25\u201329 August 2013, pp. 2718\u20132722. ISCA (2013). http:\/\/www.isca-speech.org\/archive\/interspeech_2013\/i13_2718.html","DOI":"10.21437\/Interspeech.2013-624"},{"key":"19_CR24","doi-asserted-by":"publisher","unstructured":"Kudo, T., Richardson, J.: SentencePiece: a simple and language independent subword tokenizer and Detokenizer for neural text processing. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 66\u201371. Association for Computational Linguistics, Brussels, Belgium, November 2018. https:\/\/doi.org\/10.18653\/v1\/D18-2012. https:\/\/www.aclweb.org\/anthology\/D18-2012","DOI":"10.18653\/v1\/D18-2012"},{"key":"19_CR25","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Martin, L., et al.: CamemBERT: a tasty French language model. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.acl-main.645"},{"key":"19_CR27","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":"19_CR28","doi-asserted-by":"publisher","unstructured":"Pelloin, V., et al.: End2end acoustic to semantic transduction. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7448\u20137452 (2021). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9413581","DOI":"10.1109\/ICASSP39728.2021.9413581"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Serdyuk, D., Wang, Y., Fuegen, C., Kumar, A., Liu, B., Bengio, Y.: Towards end-to-end spoken language understanding. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5754\u20135758. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461785"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Servan, C., Raymond, C., B\u00e9chet, F., Nocera, P.: Conceptual decoding from word lattices: application to the spoken dialogue corpus MEDIA. In: The Ninth International Conference on Spoken Language Processing (Interspeech 2006 - ICSLP), Pittsburgh, United States, September 2006. https:\/\/hal.archives-ouvertes.fr\/hal-01160181","DOI":"10.21437\/Interspeech.2006-451"},{"key":"19_CR31","unstructured":"Shah, P., et al.: Building a conversational agent overnight with dialogue self-play. arXiv preprint arXiv:1801.04871 (2018)"},{"key":"19_CR32","unstructured":"Simonnet, E., Ghannay, S., Camelin, N., Est\u00e8ve, Y.: Simulating ASR errors for training SLU systems. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). European Language Resources Association (ELRA), Miyazaki, Japan, May 2018. https:\/\/www.aclweb.org\/anthology\/L18-1499"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Simonnet, E., Ghannay, S., Camelin, N., Est\u00e8ve, Y., De Mori, R.: ASR error management for improving spoken language understanding. In: Interspeech 2017, Stockholm, Sweden, August 2017","DOI":"10.21437\/Interspeech.2017-1178"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Tur, G., De Mori, R.: Spoken Language Understanding: Systems for Extracting Semantic Information From Speech. Wiley (2011)","DOI":"10.1002\/9781119992691"},{"key":"19_CR35","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87802-3_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T23:44:23Z","timestamp":1632267863000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87802-3_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030878016","9783030878023"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87802-3_19","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":"22 September 2021","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":"St Petersburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","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":"27 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2021\/","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":"163","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":"74","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":"45% - 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":"3.5","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":"5.5","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)"}},{"value":"The conference was held online due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}