{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T07:55:23Z","timestamp":1743148523331,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031442124"},{"type":"electronic","value":"9783031442131"}],"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\/978-3-031-44213-1_48","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T05:01:41Z","timestamp":1695272501000},"page":"579-590","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Ternary Data, Triangle Decoding, Three Tasks, a\u00a0Multitask Learning Speech Translation Model"],"prefix":"10.1007","author":[{"given":"Linlin","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Boxing","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Shaolin","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Luo","family":"Si","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"key":"48_CR1","doi-asserted-by":"crossref","unstructured":"Anastasopoulos, A., et al.: Findings of the IWSLT 2021 evaluation campaign. In: Federico, M., Waibel, A., Costa-juss\u00e0, M.R., Niehues, J., St\u00fcker, S., Salesky, E. (eds.) Proceedings of the 18th International Conference on Spoken Language Translation, IWSLT 2021, Bangkok, Thailand (online), 5\u20136 August 2021, pp. 1\u201329. Association for Computational Linguistics (2021). https:\/\/aclanthology.org\/2021.iwslt-1.1","DOI":"10.18653\/v1\/2021.iwslt-1.1"},{"key":"48_CR2","doi-asserted-by":"publisher","unstructured":"Anastasopoulos, A., Chiang, D.: Tied multitask learning for neural speech translation. In: Walker, M.A., Ji, H., Stent, A. (eds.) Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2018, New Orleans, Louisiana, USA, 1\u20136 June 2018, vol. 1 (Long Papers), pp. 82\u201391. Association for Computational Linguistics (2018). https:\/\/doi.org\/10.18653\/v1\/n18-1008","DOI":"10.18653\/v1\/n18-1008"},{"key":"48_CR3","doi-asserted-by":"publisher","unstructured":"Bahar, P., et al.: Start-before-end and end-to-end: neural speech translation by apptek and RWTH Aachen university. In: Federico, M., Waibel, A., Knight, K., Nakamura, S., Ney, H., Niehues, J., St\u00fcker, S., Wu, D., Mariani, J., Yvon, F. (eds.) Proceedings of the 17th International Conference on Spoken Language Translation, IWSLT 2020, Online, 9\u201310 July 2020, pp. 44\u201354. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.iwslt-1.3","DOI":"10.18653\/v1\/2020.iwslt-1.3"},{"key":"48_CR4","doi-asserted-by":"publisher","unstructured":"Bapna, A., Firat, O.: Simple, scalable adaptation for neural machine translation. In: Inui, K., Jiang, J., Ng, V., Wan, X. (eds.) Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019, Hong Kong, China, 3\u20137 November 2019, pp. 1538\u20131548. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/v1\/D19-1165","DOI":"10.18653\/v1\/D19-1165"},{"key":"48_CR5","unstructured":"Berard, A., Pietquin, O., Servan, C., Besacier, L.: Listen and translate: a proof of concept for end-to-end speech-to-text translation. CoRR abs\/1612.01744 (2016). http:\/\/arxiv.org\/abs\/1612.01744"},{"key":"48_CR6","doi-asserted-by":"crossref","unstructured":"Dong, Q., Wang, M., Zhou, H., Xu, S., Xu, B., Li, L.: Consecutive decoding for speech-to-text translation. In: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, 2\u20139 February 2021, pp. 12738\u201312748. AAAI Press (2021). https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/17508","DOI":"10.1609\/aaai.v35i14.17508"},{"key":"48_CR7","doi-asserted-by":"crossref","unstructured":"Dong, Q., et al.: Listen, understand and translate: triple supervision decouples end-to-end speech-to-text translation. In: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, 2\u20139 February 2021, pp. 12749\u201312759. AAAI Press (2021). https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/17509","DOI":"10.1609\/aaai.v35i14.17509"},{"key":"48_CR8","doi-asserted-by":"publisher","unstructured":"Fang, Q., Ye, R., Li, L., Feng, Y., Wang, M.: STEMM: self-learning with speech-text manifold Mixup for speech translation. CoRR abs\/2203.10426 (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.10426","DOI":"10.48550\/arXiv.2203.10426"},{"key":"48_CR9","doi-asserted-by":"publisher","unstructured":"Gangi, M.A.D., Cattoni, R., Bentivogli, L., Negri, M., Turchi, M.: MuST-C: a multilingual speech translation corpus. In: Burstein, J., Doran, C., Solorio, T. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, 2\u20137 June 2019, vol. 1 (Long and Short Papers), pp. 2012\u20132017. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/v1\/n19-1202","DOI":"10.18653\/v1\/n19-1202"},{"key":"48_CR10","doi-asserted-by":"publisher","unstructured":"Han, C., Wang, M., Ji, H., Li, L.: Learning shared semantic space for speech-to-text translation. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Findings of the Association for Computational Linguistics: ACL\/IJCNLP 2021, Online Event, 1\u20136 August 2021. Findings of ACL, vol. ACL\/IJCNLP 2021, pp. 2214\u20132225. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.findings-acl.195","DOI":"10.18653\/v1\/2021.findings-acl.195"},{"key":"48_CR11","doi-asserted-by":"publisher","unstructured":"Inaguma, H., Kawahara, T., Watanabe, S.: Source and target bidirectional knowledge distillation for end-to-end speech translation. In: Toutanova, K., et al. (eds.) Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021, Online, 6\u201311 June 2021, pp. 1872\u20131881. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.150","DOI":"10.18653\/v1\/2021.naacl-main.150"},{"key":"48_CR12","doi-asserted-by":"publisher","unstructured":"Iranzo-S\u00e1nchez, J., Gim\u00e9nez-Pastor, A., Silvestre-Cerd\u00e0, J.A., Baquero-Arnal, P., Saiz, J.C., Juan, A.: Direct segmentation models for streaming speech translation. In: Webber, B., Cohn, T., He, Y., Liu, Y. (eds.) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, 16\u201320 November 2020, pp. 2599\u20132611. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.206","DOI":"10.18653\/v1\/2020.emnlp-main.206"},{"key":"48_CR13","doi-asserted-by":"crossref","unstructured":"Kano, T., Sakti, S., Nakamura, S.: Structured-based curriculum learning for end-to-end English-Japanese speech translation. In: Lacerda, F. (ed.) Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, 20\u201324 August 2017, pp. 2630\u20132634. ISCA (2017). http:\/\/www.isca-speech.org\/archive\/Interspeech_2017\/abstracts\/0944.html","DOI":"10.21437\/Interspeech.2017-944"},{"key":"48_CR14","unstructured":"Khan, A.R., Xu, J.: Diversity by phonetics and its application in neural machine translation. CoRR abs\/1911.04292 (2019). http:\/\/arxiv.org\/abs\/1911.04292"},{"key":"48_CR15","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Conference Track Proceedings (2015). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"48_CR16","doi-asserted-by":"publisher","unstructured":"Le, H., Pino, J.M., Wang, C., Gu, J., Schwab, D., Besacier, L.: Dual-decoder transformer for joint automatic speech recognition and multilingual speech translation. In: Scott, D., Bel, N., Zong, C. (eds.) Proceedings of the 28th International Conference on Computational Linguistics, COLING 2020, Barcelona, Spain (Online), 8\u201313 December 2020, pp. 3520\u20133533. International Committee on Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.coling-main.314","DOI":"10.18653\/v1\/2020.coling-main.314"},{"key":"48_CR17","unstructured":"Liu, Y., Zhu, J., Zhang, J., Zong, C.: Bridging the modality gap for speech-to-text translation. CoRR abs\/2010.14920 (2020). https:\/\/arxiv.org\/abs\/2010.14920"},{"key":"48_CR18","doi-asserted-by":"publisher","unstructured":"Ott, M., et al.: Fairseq: a fast, extensible toolkit for sequence modeling. In: Ammar, W., Louis, A., Mostafazadeh, N. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, 2\u20137 June 2019, Demonstrations, pp. 48\u201353. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/v1\/n19-4009","DOI":"10.18653\/v1\/n19-4009"},{"key":"48_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":"48_CR20","doi-asserted-by":"publisher","unstructured":"Park, D.S., et al.: Specaugment: a simple data augmentation method for automatic speech recognition. In: Kubin, G., Kacic, Z. (eds.) Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15\u201319 September 2019, pp. 2613\u20132617. ISCA (2019). https:\/\/doi.org\/10.21437\/Interspeech. 2019\u20132680","DOI":"10.21437\/Interspeech"},{"key":"48_CR21","doi-asserted-by":"crossref","unstructured":"Sperber, M., Neubig, G., Niehues, J., Waibel, A.: Attention-passing models for robust and data-efficient end-to-end speech translation. Trans. Assoc. Comput. Linguist. 7, 313\u2013325 (2019). https:\/\/transacl.org\/ojs\/index.php\/tacl\/article\/view\/1628","DOI":"10.1162\/tacl_a_00270"},{"key":"48_CR22","doi-asserted-by":"publisher","unstructured":"Sperber, M., Neubig, G., Pham, N., Waibel, A.: Self-attentional models for lattice inputs. In: Korhonen, A., Traum, D.R., M\u00e0rquez, L. (eds.) Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28\u20132 August 2019, Volume 1: Long Papers, pp. 1185\u20131197. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/v1\/p19-1115","DOI":"10.18653\/v1\/p19-1115"},{"issue":"2","key":"48_CR23","first-page":"116","volume":"6","author":"FW Stentiford","year":"1988","unstructured":"Stentiford, F.W., Steer, M.G.: Machine translation of speech. Br. Telecom Technol. J. 6(2), 116\u2013122 (1988)","journal-title":"Br. Telecom Technol. J."},{"key":"48_CR24","doi-asserted-by":"publisher","unstructured":"Tang, Y., Pino, J.M., Li, X., Wang, C., Genzel, D.: Improving speech translation by understanding and learning from the auxiliary text translation task. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, 1\u20136 August 2021, pp. 4252\u20134261. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.328","DOI":"10.18653\/v1\/2021.acl-long.328"},{"key":"48_CR25","doi-asserted-by":"publisher","unstructured":"Waibel, A., Jain, A.N., McNair, A.E., Saito, H., Hauptmann, A.G., Tebelskis, J.: JANUS: a speech-to-speech translation system using connectionist and symbolic processing strategies. In: 1991 International Conference on Acoustics, Speech, and Signal Processing, ICASSP \u201991, Toronto, Ontario, Canada, 14\u201317 May 1991, pp. 793\u2013796. IEEE Computer Society (1991). https:\/\/doi.org\/10.1109\/ICASSP.1991.150456","DOI":"10.1109\/ICASSP.1991.150456"},{"key":"48_CR26","doi-asserted-by":"publisher","unstructured":"Xu, C., et al.: Stacked acoustic-and-textual encoding: integrating the pre-trained models into speech translation encoders. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, 1\u20136 August 2021, pp. 2619\u20132630. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.204","DOI":"10.18653\/v1\/2021.acl-long.204"},{"key":"48_CR27","doi-asserted-by":"publisher","unstructured":"Ye, R., Wang, M., Li, L.: End-to-end speech translation via cross-modal progressive training. In: Hermansky, H., Cernock\u00fd, H., Burget, L., Lamel, L., Scharenborg, O., Motl\u00edcek, P. (eds.) Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August\u20133 September 2021, pp. 2267\u20132271. ISCA (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-1065","DOI":"10.21437\/Interspeech.2021-1065"},{"key":"48_CR28","doi-asserted-by":"publisher","unstructured":"Zhang, B., Titov, I., Haddow, B., Sennrich, R.: Adaptive feature selection for end-to-end speech translation. In: Cohn, T., He, Y., Liu, Y. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2020, Online Event, 16\u201320 November 2020. Findings of ACL, vol. EMNLP 2020, pp. 2533\u20132544. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.230","DOI":"10.18653\/v1\/2020.findings-emnlp.230"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44213-1_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T06:24:08Z","timestamp":1695277448000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44213-1_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031442124","9783031442131"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44213-1_48","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 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heraklion","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","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":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","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":"426","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":"22","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":"2.4","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"type of other papers accepted  : 9 Abstract","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)"}}]}}