{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T07:58:24Z","timestamp":1743148704462,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819981250"},{"type":"electronic","value":"9789819981267"}],"license":[{"start":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T00:00:00Z","timestamp":1699833600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T00:00:00Z","timestamp":1699833600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-99-8126-7_14","type":"book-chapter","created":{"date-parts":[[2023,11,24]],"date-time":"2023-11-24T08:05:19Z","timestamp":1700813119000},"page":"174-185","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Lead ASR Models to\u00a0Generalize Better Using Approximated Bias-Variance Tradeoff"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6482-4522","authenticated-orcid":false,"given":"Fangyuan","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Hao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhai","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,13]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Jasper: an end-to-end convolutional neural acoustic model. In: Interspeech 2019\u201320rd Annual Conference of the International Speech Communication Association (2019)","DOI":"10.21437\/Interspeech.2019-1819"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Kriman, S., et al.: QuartzNet: deep automatic speech recognition with 1D time-channel separable convolutions. In: ICASSP 2020\u201345rd IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 6124\u20136128. May 4\u20138, Barcelona, Spain (2020)","DOI":"10.1109\/ICASSP40776.2020.9053889"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Han, K.J., Pan, J., Naveen Tadala, V.K., Ma, T., Povey, D.: Multistream CNN for robust acoustic modeling. In: ICASSP 2021\u201346rd IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 6873\u20136877. Jun. 6\u201311, Toronto, Ontario, Canada (2021)","DOI":"10.1109\/ICASSP39728.2021.9414639"},{"key":"14_CR4","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 2016\u201341rd IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4960\u20134964. Mar. 20\u201325, Shanghai, China (2016)","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Rao, K., Sak, H., Prabhavalkar, R.: Exploring architectures, data and units for streaming end-to-end speech recognition with RNN-transducer. In: ASRU 2017\u20132017 IEEE Automatic Speech Recognition and Understanding Workshop, pp. 193\u2013199. Dec. 16\u201320, Okinawa, Japan (2017)","DOI":"10.1109\/ASRU.2017.8268935"},{"key":"14_CR6","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: NIPS 2017\u201331rd Conference on Neural Information Processing Systems, pp. 5998\u20136008. Dec. 4\u20139, Long Beach, California, U.S.A. (2017)"},{"key":"14_CR7","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 2018\u201343rd IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 5884\u20135888. Apr. 22\u201327, Seoul, South Korea (2018)","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Moritz, N., Hori, T., Roux, J.L.: Streaming automatic speech recognition with the transformer model. In: ICASSP 2020\u201345rd IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 6074\u20136078. May 4\u20138, Barcelona, Spain (2020)","DOI":"10.1109\/ICASSP40776.2020.9054476"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Gulati, A., Qin, J., Chiu, C.C., et al.: Conformer: convolution-augmented transformer for speech recognition. In: Interspeech 2020\u201321rd Annual Conference of the International Speech Communication Association, pp. 5036\u20135040. Oct. 25\u201330, Shanghai, China (2020)","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"14_CR10","unstructured":"Zhang, B.B., Wu, D., Yao, Z.Y., et al.: Unified streaming and non-streaming two-pass end-to-end model for speech recognition. arXiv preprint arXiv:2012.05481 (2020)"},{"key":"14_CR11","unstructured":"Wu, D., Zhang, B.B., Yang, C., et al.: U2++: unified two-pass bidirectional end-to-end model for speech recognition. arXiv preprint arXiv:2106.05642 (2021)"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"An, K., Zheng, H., Ou, Z., Xiang, H., Ding, K., Wan, G.: CUSIDE: chunking, simulating future context and decoding for streaming ASR. arXiv preprint arXiv:2203.16758 (2022)","DOI":"10.21437\/Interspeech.2022-11214"},{"key":"14_CR13","unstructured":"Ren, X., Zhu, H., Wei, L., Wu, M., Hao, J.: Improving mandarin speech recogntion with block-augmented transformer. arXiv preprint ArXiv:2207.11697 (2022)"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Wang, F., Xu, B.: Shifted chunk encoder for transformer based streaming end-to-end ASR. In: ICONIP 2022\u201329rd International Conference on Neural Information Processing, Part V, pp. 39\u201351. Nov. 22\u201326, Virtual Event, India (2022)","DOI":"10.1007\/978-981-99-1642-9_4"},{"key":"14_CR15","unstructured":"Kim, S., Gholami, A., Eaton, A., et al.: Squeezeformer: an efficient transformer for automatic speech recognition. arXiv preprint ArXiv:2206.00888 (2022)"},{"key":"14_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/neco.1992.4.1.1","volume":"4","author":"S Geman","year":"1992","unstructured":"Geman, S., Bienenstock, E., Doursa, R.: Neural networks and the bias\/variance dilemma. Neural Comput. 4, 1\u201358 (1992)","journal-title":"Neural Comput."},{"key":"14_CR17","unstructured":"Morgan, N., Bourlard, H.: Generalization and parameter estimation in feedforward netws: some experiments. In: NIPS 1990\u20134rd Conference on Neural Information Processing Systems (1990)"},{"issue":"5","key":"14_CR18","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1109\/72.248452","volume":"4","author":"R Reed","year":"1993","unstructured":"Reed, R.: Pruning algorithms-a survey. IEEE Trans. Neural Netw. 4(5), 740\u2013747 (1993)","journal-title":"IEEE Trans. Neural Netw."},{"key":"14_CR19","unstructured":"Prechelt, L.: Early stopping-but when? In Neural Networks (1996)"},{"key":"14_CR20","doi-asserted-by":"publisher","first-page":"43","DOI":"10.2478\/pralin-2018-0002","volume":"110","author":"M Popel","year":"2018","unstructured":"Popel, M., Bojar, O.: Training tips for the transformer model. The Prague Bull. Math. Linguist. 110, 43\u201370 (2018)","journal-title":"The Prague Bull. Math. Linguist."},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Yao, Z., Wu, D., Wang, X., et al.: WeNet: production oriented streaming and non-streaming end-to-end speech recognition toolkit. In: Interspeech 2021\u201322rd Annual Conference of the International Speech Communication Association, Aug. 30-Sep. 3, Brno, Czech Republic (2021)","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Park, D.S., Chan, W., Zhang, Y., Chiu, C.C., et al.: SpecAugment: a simple data augmentation method for automatic speech recognition. In: Interspeech 2019\u201320rd Annual Conference of the International Speech Communication Association, pp. 2613\u20132617. Graz, Austria (2019)","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"14_CR23","unstructured":"Bouthillier, X., Konda, K., Vincent, P., Memisevic, R.: Dropout as data augmentation. arXiv preprint arXiv:1506.08700 (2015)"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Bu, H., Du, J., Na, X., Wu, B., Zheng, H.: Aishell-1: an open-source mandarin speech corpus and a speech recognition baseline. In: O-COCOSDA 2017\u201320rd Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I\/O Systems and Assessment, pp. 1\u20135. Nov. 1\u20133, Seoul, South Korea (2015)","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"14_CR25","unstructured":"Du, J., Na, X., Liu, X., Bu, H.: AISHELL-2: transforming mandarin ASR research into industrial scale. arXiv preprint ArXiv:1808.10583 (2018)"},{"key":"14_CR26","doi-asserted-by":"publisher","first-page":"1425","DOI":"10.1162\/089976698300017232","volume":"10","author":"TM Heskes","year":"1998","unstructured":"Heskes, T.M.: Bias\/Variance decompositions for likelihood-based estimators. Neural Comput. 10, 1425\u20131433 (1998)","journal-title":"Neural Comput."},{"key":"14_CR27","unstructured":"Hoffer, E., Hubara, I., Soudry, D.: Train longer, generalize better: closing the generalization gap in large batch training of neural networks. arXiv preprint ArXiv:1705.08741 (2017)"},{"key":"14_CR28","doi-asserted-by":"publisher","first-page":"41","DOI":"10.17977\/um018v2i12019p41-46","volume":"2","author":"IKM Jais","year":"2019","unstructured":"Jais, I.K.M., Ismail, A.R., Nisa, S.Q.: Adam optimization algorithm for wide and deep neural network. Knowl. Eng. Data Sci. 2, 41\u201346 (2019)","journal-title":"Knowl. Eng. Data Sci."},{"key":"14_CR29","unstructured":"Gao, Y., Herold, Y., Yang, Z., Ney, H.: Revisiting checkpoint averaging for neural machine translation. In: AACL\/IJCNLP (2022)"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8126-7_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T11:33:36Z","timestamp":1709811216000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8126-7_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,13]]},"ISBN":["9789819981250","9789819981267"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8126-7_14","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023,11,13]]},"assertion":[{"value":"13 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Changsha","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2023.org\/","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":"1274","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":"650","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":"51% - 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":"4.14","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":"2.46","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)"}}]}}