{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T16:53:44Z","timestamp":1742921624744,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030893620"},{"type":"electronic","value":"9783030893637"}],"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\/978-3-030-89363-7_18","type":"book-chapter","created":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T01:02:59Z","timestamp":1635728579000},"page":"232-243","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Soft-BAC: Soft Bidirectional Alignment Cost for End-to-End Automatic Speech Recognition"],"prefix":"10.1007","author":[{"given":"Yonghe","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feilong","family":"Bao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanglai","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,11,1]]},"reference":[{"key":"18_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: ICML, pp. 369\u2013376. ACM (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"18_CR2","unstructured":"Graves, A., Jaitly, N.: Towards end-to-end speech recognition with recurrent neural networks. In: ICML, pp. 1764\u20131772. ACM (2014)"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Graves, A.: Sequence transduction with recurrent neural networks. In: ICML, pp. 4945\u20134949. ACM (2012)","DOI":"10.1007\/978-3-642-24797-2"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A.R., Hinton, G.: Speech recognition with deep recurrent neural networks. In: ICASSP, pp. 6645\u20136649. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Das, A., Li, J., Zhao, R., Gong, Y.: Advancing connectionist temporal classification with attention modeling. In: ICASSP, pp. 4769\u20134773. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461558"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Salazar, J., Kirchhoff, K., Huang, Z.: Self-attention networks for connectionist temporal classification in speech recognition. In: ICASSP, pp. 7115\u20137119. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682539"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Moriya, T., Sato, H., Tanaka, T., Ashihara, T., Masumura, R., Shinohara, Y.: Distilling attention weights for ctc-based asr systems. In: ICASSP, pp. 6894\u20136898. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053578"},{"key":"18_CR8","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: ICASSP, pp. 4960\u20134964. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Sak, H., Shannon, M., Rao, K., Beaufays, F.: Recurrent neural aligner: an encoder-decoder neural network model for sequence to sequence mapping. In: Interspeech, pp. 1298\u20131302 (2017)","DOI":"10.21437\/Interspeech.2017-1705"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Chiu, C.C., et al.: State-of-the-art speech recognition with sequence-to-sequence models. In: ICASSP, pp. 4774\u20134778 (2018)","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Hayashi, T., Watanabe, S., Toda, T., Takeda, K.: Multi-head decoder for end-to-end speech recognition. arXiv:1804.08050 (2018)","DOI":"10.21437\/Interspeech.2018-1655"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Dong, L., Xu, S., Xu, B.: Speech-transformer: a no-recurrence sequence-to-sequence model for speech recognition. In: ICASSP, pp. 5884\u20135888. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Karita, S., Soplin, N.E.Y., Watanabe, S., Delcroix, M., Nakatani, T.: Improving transformer-based end-to-end speech recognition with connectionist temporal classification and language model integration. In: Interspeech, pp. 1408\u20131412 (2019)","DOI":"10.21437\/Interspeech.2019-1938"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Karita, S., et al.: A comparative study on transformer vs rnn in speech applications. In: ASRU, pp. 449\u2013456. IEEE (2019)","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Pham, N.Q., Nguyen, T.S., Niehues, J., M\u00fcller, M., St\u00fcker, S., Waibel, A.: Very deep self-attention networks for end-to-end speech recognition. In: Interspeech, pp. 66\u201370 (2019)","DOI":"10.21437\/Interspeech.2019-2702"},{"key":"18_CR16","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS, pp. 5998\u20136008 (2017)"},{"key":"18_CR17","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: ICASSP, pp. 4835\u20134839 (2017)","DOI":"10.1109\/ICASSP.2017.7953075"},{"issue":"8","key":"18_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. Selected Top. Sign. Process. 11(8), 1240\u20131253 (2017)","journal-title":"IEEE J. Selected Top. Sign. Process."},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Hori, T., Watanabe, S., Yu, Z., Chan, W.: Advances in joint ctc-attention based end-to-end speech recognition with a deep cnn encoder and rnn-lm. In: Interspeech, pp. 949\u2013953 (2017)","DOI":"10.21437\/Interspeech.2017-1296"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Hori, T., Watanabe, S., Hershey, J.R.: Joint ctc\/attention decoding for end-to-end speech recognition. In: ACL, pp. 518\u2013529 (2017)","DOI":"10.18653\/v1\/P17-1048"},{"key":"18_CR21","unstructured":"Collobert, R., Puhrsch, C., Synnaeve, G.: Wav2letter: an end-to-end convnet-based speech recognition system. arXiv:1609.03193 (2016)"},{"key":"18_CR22","unstructured":"Liptchinsky, V., Synnaeve, G., Collobert, R.: Letter-based speech recognition with gated convnets. arXiv:1712.09444 (2017)"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: Librispeech: an asr corpus based on public domain audio books. In: ICASSP, pp. 5206\u20135210 (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: ACL, pp. 7\u201312 (2016)","DOI":"10.18653\/v1\/P16-1162"},{"key":"18_CR25","unstructured":"Povey, D., et al.: The kaldi speech recognition toolkit. In: ASRU. IEEE (2011)"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Park, D.S., et al.: Specaugment: a simple data augmentation method for automatic speech recognition. In: Interspeech, pp. 2613\u20132617 (2019)","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"18_CR27","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Watanabe, S., et al.: Espnet: end-to-end speech processing toolkit. In: Interspeech, pp. 2207\u20132211 (2018)","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"18_CR29","unstructured":"Zeiler, M.D.: Adadelta: an adaptive learning rate method. arXiv:1212.5701 (2012)"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Chorowski, J., Jaitly, N., Chorowski, J., Jaitly, N.: Towards better decoding and language model integration in sequence to sequence models. In: Interspeech, pp. 2207\u20132211 (2017)","DOI":"10.21437\/Interspeech.2017-343"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Bahdanau, D., Chorowski, J., Serdyuk, D., Brakel, P., Bengio, Y.: End-to-end attention-based large vocabulary speech recognition. In: ICASSP, pp. 4945\u20134949 (2016)","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"18_CR32","unstructured":"Paszke, A., et al.: Automatic differentiation in pytorch. In: Conference and Workshop on Neural Information Processing Systems (NIPS) (2017)"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2021: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-89363-7_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T01:19:45Z","timestamp":1635729585000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-89363-7_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030893620","9783030893637"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-89363-7_18","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":"1 November 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2021","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"382","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":"93","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":"24% - 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":"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)"}}]}}