{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T12:19:30Z","timestamp":1773058770831,"version":"3.50.1"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030014230","type":"print"},{"value":"9783030014247","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-01424-7_49","type":"book-chapter","created":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T17:07:37Z","timestamp":1538413657000},"page":"500-510","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Combining Articulatory Features with End-to-End Learning in Speech Recognition"],"prefix":"10.1007","author":[{"given":"Leyuan","family":"Qu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cornelius","family":"Weber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Egor","family":"Lakomkin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johannes","family":"Twiefel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Wermter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,9,27]]},"reference":[{"issue":"11","key":"49_CR1","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"49_CR2","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: Proceedings of the ICLR (2015)"},{"key":"49_CR3","doi-asserted-by":"crossref","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: Proceedings of ICCV-2011, pp. 1457\u20131464 (2011)","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"49_CR4","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/978-3-319-64680-0_13","volume-title":"New Era for Robust Speech Recognition","author":"Y Miao","year":"2017","unstructured":"Miao, Y., Metze, F.: End-to-End Architectures for Speech Recognition. In: Watanabe, S., Delcroix, M., Metze, F., Hershey, J. (eds.) New Era for Robust Speech Recognition, pp. 299\u2013323. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-64680-0_13"},{"key":"49_CR5","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 ICML-2006, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"49_CR6","doi-asserted-by":"crossref","unstructured":"Zweig, G., Yu, C., Droppo, J., et al.: Advances in all-neural speech recognition. In: Proceedings of ICASSP-2017, pp. 4805\u20134809 (2017)","DOI":"10.1109\/ICASSP.2017.7953069"},{"issue":"4","key":"49_CR7","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1006\/csla.2000.0148","volume":"14","author":"S King","year":"2000","unstructured":"King, S., Taylor, P.: Detection of phonological features in continuous speech using neural networks. Comput. Speech Lang. 14(4), 333\u2013353 (2000)","journal-title":"Comput. Speech Lang."},{"key":"49_CR8","unstructured":"Kirchhoff, K.: Robust speech recognition using articulatory information. Ph.D. thesis, University of Bielefeld (1999)"},{"key":"49_CR9","doi-asserted-by":"crossref","unstructured":"Yu, D., Siniscalchi, S.M., Deng, L., et al.: Boosting attribute and phone estimation accuracies with deep neural networks for detection-based speech recognition. In: Proceedings of ICASSP-2012, pp. 4169\u20134172 (2012)","DOI":"10.1109\/ICASSP.2012.6288837"},{"key":"49_CR10","doi-asserted-by":"crossref","unstructured":"Sak, H., Senior, A., Rao, K., et al.: Learning acoustic frame labelling for speech recognition with recurrent neural networks. In: Proceedings of ICASSP-2015, pp. 4280\u20134284 (2015)","DOI":"10.1109\/ICASSP.2015.7178778"},{"key":"49_CR11","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":"49_CR12","doi-asserted-by":"crossref","unstructured":"Bahdanau, D., Chorowski, J., Serdyuk, D., et al.: End-to-end attention-based large vocabulary speech recognition. In: Proceedings of ICASSP-2016, pp. 4945\u20134949 (2016)","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"49_CR13","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: Proceedings of ICASSP-2016, pp. 4960\u20134964 (2016)","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"49_CR14","doi-asserted-by":"crossref","unstructured":"Lee, C.-H., et al.: An overview on automatic speech attribute transcription (ASAT). In: Proceedings of INTERSPEECH-2007, pp. 1825\u20131828 (2007)","DOI":"10.21437\/Interspeech.2007-509"},{"key":"49_CR15","doi-asserted-by":"publisher","first-page":"1139","DOI":"10.1016\/j.specom.2009.05.004","volume":"51","author":"SM Siniscalchi","year":"2009","unstructured":"Siniscalchi, S.M., Lee, C.-H.: A study on integrating acoustic-phonetic information into lattice rescoring for automatic speech recognition. Speech Commun. 51, 1139\u20131153 (2009)","journal-title":"Speech Commun."},{"issue":"3","key":"49_CR16","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1109\/TASL.2011.2167610","volume":"20","author":"SM Siniscalchi","year":"2012","unstructured":"Siniscalchi, S.M., Lyu, D.C., Svendsen, T., et al.: Experiments on cross-language attribute detection and phone recognition with minimal target-specific training data. IEEE Trans. Audio Speech Lang. Process. 20(3), 875\u2013887 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"49_CR17","doi-asserted-by":"crossref","unstructured":"Ananthakrishnan, S., Narayanan, S.: Improved speech recognition using acoustic and lexical correlates of pitch accent in a n-best rescoring framework. In: Proceedings of ICASSP-2007, vol. 4, pp. IV-873\u2013IV-876 (2007)","DOI":"10.1109\/ICASSP.2007.367209"},{"key":"49_CR18","unstructured":"Rusu, A.A., Rabinowitz, N.C., Desjardins, G., et al.: Progressive neural networks. arXiv preprint arXiv:1606.04671 (2016)"},{"key":"49_CR19","unstructured":"Amodei, D., Ananthanarayanan, S., Anubhai, R., et al.: Deep speech 2: end-to-end speech recognition in English and Mandarin. In: Proceedings of ICML-2016, pp. 173\u2013182 (2016)"},{"key":"49_CR20","doi-asserted-by":"crossref","unstructured":"Sainath, T.N., Vinyals,. O., Senior, A., et al.: Convolutional, long short-term memory, fully connected deep neural networks. In: Proceedings of ICASSP-2015, pp. 4580\u20134584 (2015)","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"49_CR21","unstructured":"Jozefowicz, R., Zaremba, W., Sutskever, I.: An empirical exploration of recurrent network architectures. In: Proceedings of ICML-2015, pp. 2342\u20132350 (2015)"},{"key":"49_CR22","doi-asserted-by":"crossref","unstructured":"Paul, D.B., Baker, J.M.: The design for the wall street journal-based CSR corpus. In: Proceedings of the Workshop on Speech and Natural Language, pp. 357\u2013362 (1992)","DOI":"10.3115\/1075527.1075614"},{"key":"49_CR23","doi-asserted-by":"crossref","unstructured":"Abdel-Hamid, O., Mohamed, A., Jiang, H., et al.: Applying convolutional neural networks concepts to hybrid NN-HMM model for speech recognition. In: Proceedings of ICASSP-2012, pp. 4277\u20134280 (2012)","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"49_CR24","unstructured":"Hannun, A.Y., Maas, A.L., Jurafsky, D., et al.: First-pass large vocabulary continuous speech recognition using bi-directional recurrent DNNs. arXiv preprint arXiv:1408.2873 (2014)"},{"issue":"4","key":"49_CR25","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"S. Davis","year":"1980","unstructured":"Davis, S., Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. In: Proceedings of ICASSP-2015, pp. 357\u2013366 (1980)","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"issue":"1","key":"49_CR26","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1109\/89.650310","volume":"6","author":"L Lee","year":"1998","unstructured":"Lee, L., Rose, R.: A frequency warping approach to speaker normalization. IEEE Trans. Speech Audio Process. 6(1), 49\u201360 (1998)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"49_CR27","doi-asserted-by":"crossref","unstructured":"Vesel\u00fd, K., Ghoshal, A., Burget, L., et al.: Sequence-discriminative training of deep neural networks. In: Proceedings of INTERSPEECH-2013, pp. 2345\u20132349 (2013)","DOI":"10.21437\/Interspeech.2013-548"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01424-7_49","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T09:35:04Z","timestamp":1773048904000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01424-7_49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030014230","9783030014247"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01424-7_49","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"27 September 2018","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":"Rhodes","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":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2018\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Open","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":"360","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":"139","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":"28","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":"39% - 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","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":"In addition there are 41 full poster papers and 11 short poster papers included in the proceedings","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)"}}]}}