{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:06:07Z","timestamp":1780675567514,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Sichuan Science and Technology Program, and Fundamental Research Funds for the Central Universities of China","award":["2021SCU12050"],"award-info":[{"award-number":["2021SCU12050"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62001315, U20A20161"],"award-info":[{"award-number":["62001315, U20A20161"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Fund of Key Laboratory of Flight Techniques and Flight Safety, CAAC, China","award":["FZ2021KF04"],"award-info":[{"award-number":["FZ2021KF04"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3613759","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"213-221","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["M2ATS: A Real-world Multimodal Air Traffic Situation Benchmark Dataset and Beyond"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0393-5197","authenticated-orcid":false,"given":"Dongyue","family":"Guo","sequence":"first","affiliation":[{"name":"Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7194-5023","authenticated-orcid":false,"given":"Yi","family":"Lin","sequence":"additional","affiliation":[{"name":"Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7439-1401","authenticated-orcid":false,"given":"Xuehang","family":"You","sequence":"additional","affiliation":[{"name":"Wisesoft Co., Ltd., Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6540-4310","authenticated-orcid":false,"given":"Zhongping","family":"Yang","sequence":"additional","affiliation":[{"name":"Wisesoft Co., Ltd., Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2447-1806","authenticated-orcid":false,"given":"Jizhe","family":"Zhou","sequence":"additional","affiliation":[{"name":"Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5866-6492","authenticated-orcid":false,"given":"Bo","family":"Yang","sequence":"additional","affiliation":[{"name":"Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5491-1745","authenticated-orcid":false,"given":"Jianwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6545-4383","authenticated-orcid":false,"given":"Han","family":"Shi","sequence":"additional","affiliation":[{"name":"Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0226-6790","authenticated-orcid":false,"given":"Shasha","family":"Hu","sequence":"additional","affiliation":[{"name":"Wisesoft Co., Ltd., Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6568-4621","authenticated-orcid":false,"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International conference on machine learning. PMLR, 173--182","author":"Amodei Dario","year":"2016","unstructured":"Dario Amodei, Sundaram Ananthanarayanan, Rishita Anubhai, Jingliang Bai, Eric Battenberg, Carl Case, Jared Casper, Bryan Catanzaro, Qiang Cheng, Guoliang Chen, et al. 2016. Deep speech 2: End-to-end speech recognition in english and mandarin. In International conference on machine learning. PMLR, 173--182."},{"key":"e_1_3_2_1_2_1","volume-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1409","author":"Bahdanau Dzmitry","year":"2015","unstructured":"Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural Machine Translation by Jointly Learning to Align and Translate. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1409.0473"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"e_1_3_2_1_4_1","volume-title":"BERT for Joint Intent Classification and Slot Filling. arxiv","author":"Chen Qian","year":"1902","unstructured":"Qian Chen, Zhu Zhuo, and Wen Wang. 2019. BERT for Joint Intent Classification and Slot Filling. arxiv: 1902.10909 [cs.CL]"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952585"},{"key":"e_1_3_2_1_6_1","volume-title":"Sequence Transduction with Recurrent Neural Networks. CoRR","author":"Graves Alex","year":"2012","unstructured":"Alex Graves. 2012. Sequence Transduction with Recurrent Neural Networks. CoRR, Vol. abs\/1211.3711 (2012). showeprint[arXiv]1211.3711 http:\/\/arxiv.org\/abs\/1211.3711"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3219923"},{"key":"e_1_3_2_1_8_1","unstructured":"Dongyue Guo Jianwei Zhang and Yi Lin. 2023 b. SIA-FTP: A Spoken Instruction Aware Flight Trajectory Prediction Framework. arxiv: 2305.01661 [cs.SD]"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3572792"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639043"},{"key":"e_1_3_2_1_11_1","volume-title":"Bidirectional LSTM-CRF Models for Sequence Tagging. CoRR","author":"Huang Zhiheng","year":"1991","unstructured":"Zhiheng Huang, Wei Xu, and Kai Yu. 2015. Bidirectional LSTM-CRF Models for Sequence Tagging. CoRR, Vol. abs\/1508.01991 (2015). [arXiv]1508.01991 http:\/\/arxiv.org\/abs\/1508.01991"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2986"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/aerospace8030065"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2940992"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3015830"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.08.092"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2021.3102827"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107847"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1352"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_12"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_1_22_1","first-page":"2993","article-title":"The Airbus Air Traffic Control Speech Recognition 2018 Challenge: Towards ATC Automatic Transcription and Call Sign Detection","volume":"2019","author":"Pellegrini Thomas","year":"2019","unstructured":"Thomas Pellegrini, J\u00e9r\u00f4me Farinas, Estelle Delpech, and Francc ois Lancelot. 2019. The Airbus Air Traffic Control Speech Recognition 2018 Challenge: Towards ATC Automatic Transcription and Call Sign Detection. Proc. Interspeech 2019 (2019), 2993--2997.","journal-title":"Proc. Interspeech"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639034"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268987"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2910412"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489734"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-019-09449-5"},{"key":"e_1_3_2_1_29_1","volume-title":"Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to Sequence Learning with Neural Networks. In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, December 8-13 2014, Montreal, Quebec, Canada, Zoubin Ghahramani, Max Welling, Corinna Cortes, Neil D. Lawrence, and Kilian Q. Weinberger (Eds.). 3104--3112. https:\/\/proceedings.neurips.cc\/paper\/2014\/hash\/a14ac55a4f27472c5d894ec1c3c743d2-Abstract.html"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Puyang Xu and Ruhi Sarikaya. 2013. Exploiting shared information for multi-intent natural language sentence classification.. In Interspeech. 3785--3789.","DOI":"10.21437\/Interspeech.2013-599"},{"key":"e_1_3_2_1_32_1","first-page":"399","article-title":"ATCSpeech: A Multilingual Pilot-Controller Speech Corpus from Real Air Traffic Control Environment","volume":"2020","author":"Yang Bo","year":"2020","unstructured":"Bo Yang, Xianlong Tan, Zhengmao Chen, Bing Wang, Min Ruan, Dan Li, Zhongping Yang, Xiping Wu, and Yi Lin. 2020. ATCSpeech: A Multilingual Pilot-Controller Speech Corpus from Real Air Traffic Control Environment. Proc. Interspeech 2020 (2020), 399--403.","journal-title":"Proc. Interspeech"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108232"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3613759","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3613759","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:05:58Z","timestamp":1755821158000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3613759"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":33,"alternative-id":["10.1145\/3581783.3613759","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3613759","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}