{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T21:11:42Z","timestamp":1772658702664,"version":"3.50.1"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031202322","type":"print"},{"value":"9783031202339","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-20233-9_34","type":"book-chapter","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T00:02:48Z","timestamp":1667433768000},"page":"335-347","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["An End-to-End Conformer-Based Speech Recognition Model for Mandarin Radiotelephony Communications in Civil Aviation"],"prefix":"10.1007","author":[{"given":"Yihua","family":"Shi","sequence":"first","affiliation":[]},{"given":"Guanglin","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Jin","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Haigang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jinfeng","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,3]]},"reference":[{"issue":"4","key":"34_CR1","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1207\/S15327108IJAP1204_2","volume":"12","author":"OV Prinzo","year":"2002","unstructured":"Prinzo, O.V., Morrow, D.G.: Improving pilot\/air traffic control voice communication in general aviation. Int. J. Aviat. Psychol. 12(4), 341\u2013357 (2002)","journal-title":"Int. J. Aviat. Psychol."},{"issue":"12","key":"34_CR2","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.3357\/ASEM.2468.2010","volume":"81","author":"TM Lahtinen","year":"2010","unstructured":"Lahtinen, T.M., Huttunen, K.H., Kuronen, P.O., Sorri, M.J., Leino, T.K.: Radio speech communication problems reported in a survey of military pilots. Aviat. Space Environ. Med. 81(12), 1123\u20131127 (2010)","journal-title":"Aviat. Space Environ. Med."},{"issue":"12","key":"34_CR3","doi-asserted-by":"publisher","first-page":"2280","DOI":"10.1016\/j.cja.2018.10.001","volume":"31","author":"G Jia","year":"2018","unstructured":"Jia, G., Cheng, F., Yang, J., Li, D.: Intelligent checking model of Chinese radiotelephony read-backs in civil aviation air traffic control. Chin. J. Aeronaut. 31(12), 2280\u20132289 (2018)","journal-title":"Chin. J. Aeronaut."},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Lu, Y., Shi, Y., Jia, G., Yang, J.: A new method for semantic consistency verification of aviation radiotelephony communication based on LSTM-RNN. In: 2016 IEEE International Conference on Digital Signal Processing (DSP), pp. 422\u2013426. IEEE Press, New York (2016)","DOI":"10.1109\/ICDSP.2016.7868592"},{"key":"34_CR5","unstructured":"Illman, P.E., Gailey, G.: Pilot\u2019s Radio communications Handbook, 6th edn. McGraw-Hill Professional (2012)"},{"key":"34_CR6","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: NIPS 2017, pp. 6000\u20136010. Red Hook, New York (2017)"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Gulati, A., Qin, J., Chiu, C.C., et al.: Conformer: convolution-augmented transformer for speech recognition. In: Proceedings Interspeech 2020, pp. 5036\u20135040 (2020)","DOI":"10.21437\/Interspeech.2020-3015"},{"issue":"4","key":"34_CR8","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1109\/PROC.1976.10159","volume":"64","author":"F Jelinek","year":"1976","unstructured":"Jelinek, F.: Continuous speech recognition by statistical methods. Proc. IEEE 64(4), 532\u2013556 (1976)","journal-title":"Proc. IEEE"},{"issue":"6","key":"34_CR9","doi-asserted-by":"publisher","first-page":"1235","DOI":"10.1002\/j.1538-7305.1985.tb00273.x","volume":"64","author":"BH Juang","year":"1985","unstructured":"Juang, B.H.: Maximum-likelihood estimation for mixture multivariate stochastic observations of Markov chains. AT&T Techn. J. 64(6), 1235\u20131249 (1985)","journal-title":"AT&T Techn. J."},{"issue":"6","key":"34_CR10","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., Deng, L., Yu, D., et al.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82\u201397 (2012)","journal-title":"IEEE Signal Process. Mag."},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Li, J.: Recent advances in end-to-end automatic speech recognition. arXiv preprint arXiv: 2111.01690 (2022)","DOI":"10.1561\/116.00000050"},{"key":"34_CR12","unstructured":"Hannun, A.: The history of speech recognition to the year 2030. arXiv preprint arXiv: 2108.00084 (2021)"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Graves, A., Fernandez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: 23rd International Conference on Machine Learning, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"34_CR14","doi-asserted-by":"publisher","unstructured":"Graves, A.: Connectionist temporal classification. In: Supervised Sequence Labelling with Recurrent Neural Networks. Studies in Computational Intelligence. LNCS, vol. 385, pp. 61\u201393. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-24797-2_7","DOI":"10.1007\/978-3-642-24797-2_7"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Graves, A.: Sequence transduction with recurrent neural networks. arXiv preprint arXiv: 1211.3711 (2012)","DOI":"10.1007\/978-3-642-24797-2"},{"key":"34_CR16","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 (2016)","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"34_CR17","unstructured":"Chorowski, J., Bahdanau, D., Serdyuk, D., Cho, K., Bengio, Y.: Attention-based models for speech recognition. In: 28th International Conference on Neural Information Processing Systems, pp. 577\u2013585 (2015)"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Y., Guo, X., Zhang, H., Yang, J.: An acoustic model of civil aviation\u2019s radiotelephony communication. In: 8th International Conference on Computing and Pattern Recognition (ICCPR 2019), pp. 315\u2013319 (2019)","DOI":"10.1145\/3373509.3373557"},{"key":"34_CR19","unstructured":"Qiu, Y., Jia, G., Yang, J., Liu, Y.: Speech recognition model of civil aviation radiotelephony communication based on BiLSTM. J. Sig. Process. 35(02), 293\u2013300 (2019). (in Chinese)"},{"key":"34_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/978-3-030-36204-1_15","volume-title":"Intelligence Science and Big Data Engineering. Big Data and Machine Learning","author":"K Zhou","year":"2019","unstructured":"Zhou, K., Yang, Q., Sun, X., Liu, S., Lu, J.: Improved CTC-attention based end-to-end speech recognition on air traffic control. In: Cui, Z., Pan, J., Zhang, S., Xiao, L., Yang, J. (eds.) IScIDE 2019. LNCS, vol. 11936, pp. 187\u2013196. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-36204-1_15"},{"key":"34_CR21","volume-title":"Artificial Intelligence Speech Recognition Understanding and Practice","author":"D Yu","year":"2020","unstructured":"Yu, D., Deng, L., Yu, K., Qian, Y.: Artificial Intelligence Speech Recognition Understanding and Practice. Publishing House of Electronics Industry, Beijing (2020).(in Chinese)"},{"key":"34_CR22","unstructured":"Povey, D., Ghoshal, A., Boulianne, G., et al.: The Kaldi speech recognition toolkit. In: 2011 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU 2011). IEEE Signal Processing Society (2011)"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q., Salakhutdinov, R.: Transformer-XL: attentive language models beyond a fixed-length context. In: 57th Annual Meeting of the Association for Computational Linguistics, pp. 2978\u20132988 (2019)","DOI":"10.18653\/v1\/P19-1285"}],"container-title":["Lecture Notes in Computer Science","Biometric Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20233-9_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T00:30:38Z","timestamp":1667435438000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20233-9_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031202322","9783031202339"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20233-9_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"3 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCBR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Biometric Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccbr2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ccbr99.cn\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"115","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":"70","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":"61% - 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":"3","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)"}}]}}