{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T13:26:35Z","timestamp":1726061195296},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030362034"},{"type":"electronic","value":"9783030362041"}],"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\/978-3-030-36204-1_15","type":"book-chapter","created":{"date-parts":[[2019,11,28]],"date-time":"2019-11-28T09:03:54Z","timestamp":1574931834000},"page":"187-196","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Improved CTC-Attention Based End-to-End Speech Recognition on Air Traffic Control"],"prefix":"10.1007","author":[{"given":"Kai","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"XiuSong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"ShaoHan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"JinJun","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,11,29]]},"reference":[{"issue":"2","key":"15_CR1","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"LR Rabiner","year":"1989","unstructured":"Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77(2), 257\u2013286 (1989)","journal-title":"Proc. IEEE"},{"key":"15_CR2","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. IEEE Sig. Process. Mag. 29, 82\u201397 (2012)","journal-title":"IEEE Sig. Process. Mag."},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., 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":"15_CR4","unstructured":"Graves, A., Jaitly, N.: Towards end-to-end speech recognition with recurrent neural networks. In: International Conference on Machine Learning, pp. 1764\u20131772 (2014)"},{"key":"15_CR5","unstructured":"Hannun, A., Case, C., Casper, J., et al.: Deep speech: scaling up end-to-end speech recognition. arXiv preprint \narXiv:1412.5567\n\n (2014)"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Miao, Y., Gowayyed, M., Metze, F.: EESEN: end-to-end speech recognition using deep RNN models and WFST-based decoding. In: 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 167\u2013174. IEEE (2015)","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"15_CR7","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint \narXiv:1409.0473\n\n (2014)"},{"key":"15_CR8","unstructured":"Chorowski, J., Bahdanau, D., Cho, K., et al.: End-to-end continuous speech recognition using attention-based recurrent NN: first results. arXiv preprint \narXiv:1412.1602\n\n (2014)"},{"key":"15_CR9","unstructured":"Chorowski, J.K., Bahdanau, D., Serdyuk, D., et al.: Attention-based models for speech recognition. In: Advances in Neural Information Processing Systems, pp. 577\u2013585 (2015)"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Chan, W., Jaitly, N., Le, Q., et al.: 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":"15_CR11","doi-asserted-by":"crossref","unstructured":"Bahdanau, D., Chorowski, J., Serdyuk, D., et al.: End-to-end attention-based large vocabulary speech recognition. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4945\u20134949. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Kim, S., Hori, T., Watanabe, S.: Joint CTC-attention based end-to-end speech recognition using multi-task learning. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4835\u20134839. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"15_CR13","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint \narXiv:1409.1556\n\n (2014)"},{"key":"15_CR14","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/978-1-4842-2766-4_12","volume-title":"Deep Learning with Python","author":"Nikhil Ketkar","year":"2017","unstructured":"Ketkar, N.: Introduction to PyTorch. In: Deep Learning with Python, pp. 195\u2013208. Apress, Berkeley (2017)"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Watanabe, S., Hori, T., Karita, S., et al.: ESPnet: end-to-end speech processing toolkit. arXiv preprint \narXiv:1804.00015\n\n (2018)","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Shan, C., Zhang, J., Wang, Y., et al.: Attention-based end-to-end speech recognition on voice search. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4764\u20134768. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462492"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Hinton, G., Van Camp, D.: Keeping neural networks simple by minimizing the description length of the weights. In: Proceedings of the 6th Annual ACM Conference on Computational Learning Theory (1993)","DOI":"10.1145\/168304.168306"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Ghahremani, P., BabaAli, B., Povey, D., et al.: A pitch extraction algorithm tuned for automatic speech recognition. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2494\u20132498. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6854049"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Miao, Y., Gowayyed, M., Na, X., et al.: An empirical exploration of CTC acoustic models. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2623\u20132627. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472152"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Hori, T., Watanabe, S., Zhang, Y., et al.: Advances in joint CTC-attention based end-to-end speech recognition with a deep CNN encoder and RNN-LM. arXiv preprint \narXiv:1706.02737\n\n (2017)","DOI":"10.21437\/Interspeech.2017-1296"}],"container-title":["Lecture Notes in Computer Science","Intelligence Science and Big Data Engineering. Big Data and Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-36204-1_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,11,28]],"date-time":"2019-11-28T09:09:04Z","timestamp":1574932144000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-36204-1_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030362034","9783030362041"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-36204-1_15","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":"29 November 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IScIDE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Science and Big Data Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanjing","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":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iscide2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iscide.njust.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}