{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T15:31:43Z","timestamp":1742916703041,"version":"3.40.3"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030878016"},{"type":"electronic","value":"9783030878023"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-87802-3_71","type":"book-chapter","created":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T23:36:52Z","timestamp":1632267412000},"page":"795-806","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Induced Local Attention for Transformer Models in Speech Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3552-3325","authenticated-orcid":false,"given":"Tobias","family":"Watzel","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5312-3870","authenticated-orcid":false,"given":"Ludwig","family":"K\u00fcrzinger","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0641-3178","authenticated-orcid":false,"given":"Lujun","family":"Li","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":[[2021,9,22]]},"reference":[{"key":"71_CR1","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":"71_CR2","doi-asserted-by":"crossref","unstructured":"Gulati, A., et al.: Conformer: convolution-augmented transformer for speech recognition. arXiv preprint arXiv:2005.08100 (2020)","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"71_CR3","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"71_CR4","doi-asserted-by":"crossref","unstructured":"Ko, T., Peddinti, V., Povey, D., Khudanpur, S.: Audio augmentation for speech recognition. In: Sixteenth Annual Conference of the International Speech Communication Association (2015)","DOI":"10.21437\/Interspeech.2015-711"},{"key":"71_CR5","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., Manning, C.D.: Effective Approaches to Attention-Based Neural Machine Translation. arXiv preprint arXiv:1508.04025 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"71_CR6","doi-asserted-by":"crossref","unstructured":"Nguyen, T.T., Nguyen, X.P., Joty, S., Li, X.: Differentiable window for dynamic local attention. arXiv preprint arXiv:2006.13561 (2020)","DOI":"10.18653\/v1\/2020.acl-main.589"},{"key":"71_CR7","doi-asserted-by":"crossref","unstructured":"Park, D.S., et al.: Specaugment: a simple data augmentation method for automatic speech recognition. arXiv preprint arXiv:1904.08779 (2019)","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"71_CR8","unstructured":"Povey, D., et al.: The Kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding. No. CONF, IEEE Signal Processing Society (2011)"},{"key":"71_CR9","unstructured":"Rousseau, A., Del\u00e9glise, P., Esteve, Y.: Enhancing the TED-LIUM corpus with selected data for language modeling and more TED talks. In: LREC, pp. 3935\u20133939 (2014)"},{"key":"71_CR10","doi-asserted-by":"crossref","unstructured":"Salazar, J., Kirchhoff, K., Huang, Z.: Self-attention networks for connectionist temporal classification in speech recognition. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7115\u20137119. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682539"},{"key":"71_CR11","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909 (2015)","DOI":"10.18653\/v1\/P16-1162"},{"key":"71_CR12","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations. arXiv preprint arXiv:1803.02155 (2018)","DOI":"10.18653\/v1\/N18-2074"},{"key":"71_CR13","doi-asserted-by":"crossref","unstructured":"Sperber, M., Niehues, J., Neubig, G., St\u00fcker, S., Waibel, A.: Self-attentional acoustic models. arXiv preprint arXiv:1803.09519 (2018)","DOI":"10.21437\/Interspeech.2018-1910"},{"issue":"1","key":"71_CR14","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"71_CR15","unstructured":"Sutskever, I., Vinyals, O., Le, Q.: Sequence to sequence learning with neural networks. In: Advances in NIPS (2014)"},{"key":"71_CR16","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"71_CR17","doi-asserted-by":"crossref","unstructured":"Tian, Z., Yi, J., Tao, J., Bai, Y., Wen, Z.: Self-attention transducers for end-to-end speech recognition. In: Proceedings of Interspeech 2019, pp. 4395\u20134399 (2019)","DOI":"10.21437\/Interspeech.2019-2203"},{"key":"71_CR18","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"71_CR19","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"},{"key":"71_CR20","doi-asserted-by":"crossref","unstructured":"Yang, B., Tu, Z., Wong, D.F., Meng, F., Chao, L.S., Zhang, T.: Modeling localness for self-attention networks. arXiv preprint arXiv:1810.10182 (2018)","DOI":"10.18653\/v1\/D18-1475"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87802-3_71","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T23:59:34Z","timestamp":1632268774000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87802-3_71"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030878016","9783030878023"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87802-3_71","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"22 September 2021","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":"St Petersburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2021\/","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":"163","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":"74","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":"45% - 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":"3.5","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":"5.5","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)"}},{"value":"The conference was held online due to the COVID-19 pandemic.","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)"}}]}}