{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:24:36Z","timestamp":1763202276039,"version":"3.37.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030260606"},{"type":"electronic","value":"9783030260613"}],"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\/978-3-030-26061-3_27","type":"book-chapter","created":{"date-parts":[[2019,8,8]],"date-time":"2019-08-08T23:03:54Z","timestamp":1565305434000},"page":"258-269","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Exploring Hybrid CTC\/Attention End-to-End Speech Recognition with Gaussian Processes"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5312-3870","authenticated-orcid":false,"given":"Ludwig","family":"K\u00fcrzinger","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3552-3325","authenticated-orcid":false,"given":"Tobias","family":"Watzel","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0641-3178","authenticated-orcid":false,"given":"Lujun","family":"Li","sequence":"additional","affiliation":[]},{"given":"Robert","family":"Baumgartner","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1096-1596","authenticated-orcid":false,"given":"Gerhard","family":"Rigoll","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,7,24]]},"reference":[{"key":"27_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"27_CR2","unstructured":"Bengio, S., Vinyals, O., Jaitly, N., Shazeer, N.: Scheduled sampling for sequence prediction with recurrent neural networks. In: Advances in Neural Information Processing Systems, pp. 1171\u20131179 (2015)"},{"issue":"Feb","key":"27_CR3","first-page":"281","volume":"13","author":"J Bergstra","year":"2012","unstructured":"Bergstra, J., Bengio, Y.: Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13(Feb), 281\u2013305 (2012)","journal-title":"J. Mach. Learn. Res."},{"key":"27_CR4","unstructured":"Bergstra, J.S., Bardenet, R., Bengio, Y., K\u00e9gl, B.: Algorithms for hyper-parameter optimization. In: Advances in Neural Information Processing Systems, pp. 2546\u20132554 (2011)"},{"issue":"5","key":"27_CR5","doi-asserted-by":"publisher","first-page":"1190","DOI":"10.1137\/0916069","volume":"16","author":"RH Byrd","year":"1995","unstructured":"Byrd, R.H., Lu, P., Nocedal, J., Zhu, C.: A limited memory algorithm for bound constrained optimization. SIAM J. Sci. Comput. 16(5), 1190\u20131208 (1995). https:\/\/doi.org\/10\/bpjm24","journal-title":"SIAM J. Sci. Comput."},{"key":"27_CR6","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. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"27_CR7","unstructured":"Chorowski, J.K., Bahdanau, D., Serdyuk, D., Cho, K., Bengio, Y.: Attention-based models for speech recognition. In: Neural Information Processing Systems, pp. 577\u2013585 (2015)"},{"key":"27_CR8","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_3"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: 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":"27_CR10","unstructured":"Gulcehre, C., et al.: On using monolingual corpora in neural machine translation. arXiv preprint arXiv:1503.03535 (2015)"},{"key":"27_CR11","doi-asserted-by":"crossref","unstructured":"Lu, L., Kong, L., Dyer, C., Smith, N.A.: Multitask learning with CTC and segmental CRF for speech recognition (2017). https:\/\/doi.org\/10\/gf3hs6","DOI":"10.21437\/Interspeech.2017-71"},{"key":"27_CR12","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/978-3-540-28650-9_4","volume-title":"Advanced Lectures on Machine Learning","author":"CE Rasmussen","year":"2004","unstructured":"Rasmussen, C.E.: Gaussian processes in machine learning. In: Bousquet, O., von Luxburg, U., R\u00e4tsch, G. (eds.) ML -2003. LNCS (LNAI), vol. 3176, pp. 63\u201371. Springer, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-540-28650-9_4"},{"key":"27_CR13","unstructured":"Rousseau, A., Del\u00e9glise, P., Est\u00e8ve, Y.: Enhancing the TED-LIUM corpus with selected data for language modeling and more TED talks. In: LREC, pp. 3935\u20133939 (2014)"},{"key":"27_CR14","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"27_CR15","unstructured":"Snoek, J., Larochelle, H., Adams, R.P.: Practical Bayesian optimization of machine learning algorithms. In: Advances in Neural Information Processing Systems, pp. 2951\u20132959 (2012)"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Toshniwal, S., Kannan, A., Chiu, C.C., Wu, Y., Sainath, T.N., Livescu, K.: A comparison of techniques for language model integration in encoder-decoder speech recognition. In: 2018 IEEE Spoken Language Technology Workshop (SLT), pp. 369\u2013375. IEEE (2018)","DOI":"10.1109\/SLT.2018.8639038"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Watanabe, S., et al.: ESPnet: end-to-end speech processing toolkit. arXiv preprint arXiv:1804.00015 (2018)","DOI":"10.21437\/Interspeech.2018-1456"},{"issue":"8","key":"27_CR18","doi-asserted-by":"publisher","first-page":"1240","DOI":"10.1109\/JSTSP.2017.2763455","volume":"11","author":"S Watanabe","year":"2017","unstructured":"Watanabe, S., Hori, T., Kim, S., Hershey, J.R., Hayashi, T.: Hybrid CTC\/attention architecture for end-to-end speech recognition. IEEE J. Sel. Top. Signal Process. 11(8), 1240\u20131253 (2017). https:\/\/doi.org\/10\/gcm8hv","journal-title":"IEEE J. Sel. Top. Signal Process."},{"issue":"2","key":"27_CR19","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1162\/neco.1989.1.2.270","volume":"1","author":"RJ Williams","year":"1989","unstructured":"Williams, R.J., Zipser, D.: A learning algorithm for continually running fully recurrent neural networks. Neural Comput. 1(2), 270\u2013280 (1989). https:\/\/doi.org\/10\/chwnmt","journal-title":"Neural Comput."}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-26061-3_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,25]],"date-time":"2022-09-25T10:28:54Z","timestamp":1664101734000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-26061-3_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030260606","9783030260613"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-26061-3_27","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":"24 July 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Istanbul","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turkey","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":"20 August 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2019\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"86","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":"57","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":"66% - 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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}