{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T17:32:42Z","timestamp":1755797562589,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030782917"},{"type":"electronic","value":"9783030782924"}],"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\/978-3-030-78292-4_25","type":"book-chapter","created":{"date-parts":[[2021,6,10]],"date-time":"2021-06-10T21:03:59Z","timestamp":1623359039000},"page":"306-317","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Good Start is Half the Battle Won: Unsupervised Pre-training for Low Resource Children\u2019s Speech Recognition for an Interactive Reading Companion"],"prefix":"10.1007","author":[{"given":"Abhinav","family":"Misra","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anastassia","family":"Loukina","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beata","family":"Beigman Klebanov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Binod","family":"Gyawali","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Klaus","family":"Zechner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,6,11]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Atal, B., Schroeder, M.: Predictive coding of speech signals and subjective error criteria. In: ICASSP \u201978. IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 3, pp. 573\u2013576 (1978)","DOI":"10.1109\/TASSP.1979.1163237"},{"issue":"3","key":"25_CR2","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1177\/0013164411412590","volume":"72","author":"J Balogh","year":"2012","unstructured":"Balogh, J., Bernstein, J., Cheng, J., Moere, A.V., Townshend, B., Suzuki, M.: Validation of automated scoring of oral reading. Educ. Psychol. Measur. 72(3), 435\u2013452 (2012)","journal-title":"Educ. Psychol. Measur."},{"issue":"8","key":"25_CR3","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798\u20131828 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"25_CR4","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.1037\/a0031479","volume":"105","author":"D Bola\u00f1os","year":"2013","unstructured":"Bola\u00f1os, D., Cole, R., Ward, W., Tindal, G., Hasbrouck, J., Schwanenflugel, P.: Human and automated assessment of oral reading fluency. J. Educ. Psychol. 105, 1142 (2013). https:\/\/doi.org\/10.1037\/a0031479","journal-title":"J. Educ. Psychol."},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, J.: Real-time scoring of an oral reading assessment on mobile devices. In: INTERSPEECH (2018)","DOI":"10.21437\/Interspeech.2018-34"},{"key":"25_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4324\/9781315647500","volume-title":"Adaptive Educational technologies for literacy instruction","author":"SA Crossley","year":"2016","unstructured":"Crossley, S.A., McNamara, D.: Educational technologies and literacy development. In: Crossley, S.A., Mcnamara, D. (eds.) Adaptive Educational technologies for literacy instruction, pp. 1\u201312. Routledge, New York (2016)"},{"key":"25_CR7","unstructured":"Das, S., Nix, D., Picheny, M.: Improvements in children\u2019s speech recognition performance. In: Proceedings of IEEE ICASSP (1998)"},{"issue":"4","key":"25_CR8","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2011","unstructured":"Dehak, N., Kenny, P.J., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19(4), 788\u2013798 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"25_CR10","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. ArXiv abs\/1810.04805 (2019)"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1422\u20131430 (2015)","DOI":"10.1109\/ICCV.2015.167"},{"issue":"10","key":"25_CR12","doi-asserted-by":"publisher","first-page":"832","DOI":"10.1016\/j.specom.2009.04.005","volume":"51","author":"M Eskenazi","year":"2009","unstructured":"Eskenazi, M.: An overview of spoken language technology for education. Speech Commun. 51(10), 832\u2013844 (2009). https:\/\/doi.org\/10.1016\/j.specom.2009.04.005","journal-title":"Speech Commun."},{"key":"25_CR13","first-page":"297","volume":"9","author":"M Gutmann","year":"2010","unstructured":"Gutmann, M., Hyv\u00e4rinen, A.: Noise-contrastive estimation: a new estimation principle for unnormalized statistical models. J. Mach. Learn. Res. - Proc. Track 9, 297\u2013304 (2010)","journal-title":"J. Mach. Learn. Res. - Proc. Track"},{"issue":"6","key":"25_CR14","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., et al.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Sig. Process. Mag. 29(6), 82\u201397 (2012). https:\/\/doi.org\/10.1109\/MSP.2012.2205597","journal-title":"IEEE Sig. Process. Mag."},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Kunze, J., Kirsch, L., Kurenkov, I., Krug, A., Johannsmeier, J., Stober, S.: Transfer learning for speech recognition on a budget. In: ACL (2017)","DOI":"10.18653\/v1\/W17-2620"},{"key":"25_CR16","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. ArXiv abs\/1907.11692 (2019)"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Madnani, N., et al.: MyTurnToRead: an interleaved e-book reading tool for developing and struggling readers. In: Proceedings of the 57th Conference of the Association for Computational Linguistics: System Demonstrations, pp. 141\u2013146. Association for Computational Linguistics, Florence (2019). https:\/\/www.aclweb.org\/anthology\/P19-3024","DOI":"10.18653\/v1\/P19-3024"},{"key":"25_CR18","unstructured":"Mostow, J.: Why and how our automated reading tutor listens. In: Proceedings of the International Symposium on Automatic Detection of Errors in Pronunciation Training, pp. 43\u201352 (2012)"},{"key":"25_CR19","doi-asserted-by":"publisher","first-page":"61","DOI":"10.2190\/06AX-QW99-EQ5G-RDCF","volume":"29","author":"J Mostow","year":"2003","unstructured":"Mostow, J., et al.: Evaluation of an automated reading tutor that listens: comparison to human tutoring and classroom instruction. J. Educ. Comput. Res. 29, 61\u2013117 (2003). https:\/\/doi.org\/10.2190\/06AX-QW99-EQ5G-RDCF","journal-title":"J. Educ. Comput. Res."},{"key":"25_CR20","unstructured":"van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. ArXiv (2018)"},{"key":"25_CR21","doi-asserted-by":"publisher","unstructured":"O\u2019Shaughnessy, D.: Invited paper: automatic speech recognition: history, methods and challenges. Pattern Recognit. 41(10), 2965\u20132979 (2008). https:\/\/doi.org\/10.1016\/j.patcog.2008.05.008. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0031320308001799","DOI":"10.1016\/j.patcog.2008.05.008"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: Librispeech: an ASR corpus based on public domain audio books. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5206\u20135210 (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"issue":"3","key":"25_CR23","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1109\/LSP.2017.2723507","volume":"25","author":"V Peddinti","year":"2018","unstructured":"Peddinti, V., Wang, Y., Povey, D., Khudanpur, S.: Low latency acoustic modeling using temporal convolution and LSTMs. IEEE Sig. Process. Lett. 25(3), 373\u2013377 (2018)","journal-title":"IEEE Sig. Process. Lett."},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Potamianos, A., Narayanan, S., Lee, S.: Automatic speech recognition for children. In: Proceedings of Eurospeech (1997)","DOI":"10.21437\/Eurospeech.1997-623"},{"key":"25_CR25","unstructured":"Povey, D., et al.: The Kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding (2011)"},{"key":"25_CR26","doi-asserted-by":"publisher","unstructured":"Povey, D., et al.: Purely sequence-trained neural networks for ASR based on lattice-free mmi, pp. 2751\u20132755 (2016). https:\/\/doi.org\/10.21437\/Interspeech. 2016\u2013595","DOI":"10.21437\/Interspeech"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Schneider, S., Baevski, A., Collobert, R., Auli, M.: wav2vec: unsupervised pre-training for speech recognition. In: INTERSPEECH (2019)","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Schroeder, M., Atal, B.: Code-excited linear prediction (CELP): high-quality speech at very low bit rates. In: ICASSP \u201985. IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 10, pp. 937\u2013940 (1985)","DOI":"10.1109\/ICASSP.1985.1168147"},{"key":"25_CR29","unstructured":"Shivakumar, P.G., Potamianos, A., Lee, S., Narayanan, S.: Improving speech recognition for children using acoustic adaptation and pronunciation modeling. In: Proceedings of the INTERSPEECH Workshop on Child, Computer, and Interaction (2014)"},{"key":"25_CR30","volume-title":"Preventing Reading Difficulties in Young Children","author":"CE Snow","year":"1998","unstructured":"Snow, C.E., Burns, M.S., Griffin, P.: Preventing Reading Difficulties in Young Children. National Academy Press, Washington, D.C. (1998)"},{"key":"25_CR31","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1007\/3-540-45433-0_16","volume-title":"Advances in Natural Language Processing","author":"N Souto","year":"2002","unstructured":"Souto, N., Meinedo, H., Neto, J.P.: Building language models for continuous speech recognition systems. In: Ranchhod, E., Mamede, N.J. (eds.) PorTAL 2002. LNCS (LNAI), vol. 2389, pp. 101\u2013110. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-45433-0_16"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. In: EMNLP (2018)","DOI":"10.18653\/v1\/W18-5446"},{"key":"25_CR33","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., Le, Q.V.: XlNet: generalized autoregressive pretraining for language understanding (2019). http:\/\/arxiv.org\/abs\/1906.08237. cite arxiv:1906.08237 Comment: Pretrained models and code are available at https:\/\/github.com\/zihangdai\/xlnet"},{"key":"25_CR34","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-5779-3","volume-title":"Automatic Speech Recognition","author":"D Yu","year":"2016","unstructured":"Yu, D., Deng, L.: Automatic Speech Recognition. Springer, Heidelberg (2016). https:\/\/doi.org\/10.1007\/978-1-4471-5779-3"},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Zechner, K., Sabatini, J., Chen, L.: Automatic scoring of children\u2019s read-aloud text passages and word lists. In: Proceedings of the NAACL-HLT Workshop on Innovative Use of NLP for Building Educational Applications, pp. 10\u201318 (2009)","DOI":"10.3115\/1609843.1609845"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in Education"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-78292-4_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T16:01:50Z","timestamp":1725206510000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-78292-4_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030782917","9783030782924"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-78292-4_25","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":"11 June 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIED","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Intelligence in Education","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Utrecht","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","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":"14 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 June 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aied2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aied2021.science.uu.nl\/","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":"209","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":"40","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":"76","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":"19% - 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","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)"}},{"value":"Due to the COVID-19 pandemic the conference was held online.","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)"}}]}}