{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T19:06:49Z","timestamp":1763924809709,"version":"3.44.0"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030863364"},{"type":"electronic","value":"9783030863371"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-86337-1_32","type":"book-chapter","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T20:48:12Z","timestamp":1630702092000},"page":"478-493","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["TS-Net: OCR Trained to Switch Between Text Transcription Styles"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0774-8903","authenticated-orcid":false,"given":"Jan","family":"Koh\u00fat","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6364-129X","authenticated-orcid":false,"given":"Michal","family":"Hradi\u0161","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"key":"32_CR1","doi-asserted-by":"crossref","unstructured":"Bell, P., Fainberg, J., Klejch, O., Li, J., Renals, S., Swietojanski, P.: Adaptation algorithms for speech recognition: an overview (2020)","DOI":"10.1109\/OJSP.2020.3045349"},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Bluche, T., Messina, R.: Gated convolutional recurrent neural networks for multilingual handwriting recognition. In: ICDAR 2017, vol. 01, pp. 646\u2013651 (2017)","DOI":"10.1109\/ICDAR.2017.111"},{"key":"32_CR3","doi-asserted-by":"crossref","unstructured":"Causer, T., Grint, K., Sichani, A.M., Terras, M.: \u2018Making such bargain\u2019: transcribe Bentham and the quality and cost-effectiveness of crowdsourced transcription. Digit. Sch. Hum. 33(3), 467\u2013487 (2018)","DOI":"10.1093\/llc\/fqx064"},{"key":"32_CR4","unstructured":"Chowdhury, A., Vig, L.: An efficient end-to-end neural model for handwritten text recognition. CoRR abs\/1807.07965 (2018)"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Cui, X., Goel, V., Saon, G.: Embedding-based speaker adaptive training of deep neural networks. CoRR abs\/1710.06937 (2017)","DOI":"10.21437\/Interspeech.2017-460"},{"issue":"5","key":"32_CR6","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1109\/TASLP.2018.2798821","volume":"26","author":"M Delcroix","year":"2018","unstructured":"Delcroix, M., Kinoshita, K., Ogawa, A., Huemmer, C., Nakatani, T.: Context adaptive neural network based acoustic models for rapid adaptation. IEEE\/ACM Trans. Audio Speech Lang. Process. 26(5), 895\u2013908 (2018)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"32_CR7","unstructured":"Dumoulin, V., Shlens, J., Kudlur, M.: A learned representation for artistic style. CoRR abs\/1610.07629 (2016)"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Dutta, K., Krishnan, P., Mathew, M., Jawahar, C.V.: Improving CNN-RNN hybrid networks for handwriting recognition. In: ICFHR 2018, pp. 80\u201385 (2018)","DOI":"10.1109\/ICFHR-2018.2018.00023"},{"issue":"10\u201311","key":"32_CR9","doi-asserted-by":"publisher","first-page":"827","DOI":"10.1016\/j.specom.2006.11.005","volume":"49","author":"R Gemello","year":"2007","unstructured":"Gemello, R., Mana, F., Scanzio, S., Laface, P., De Mori, R.: Linear hidden transformations for adaptation of hybrid ANN\/HMM models. Speech Commun. 49(10\u201311), 827\u2013835 (2007)","journal-title":"Speech Commun."},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lee, H., Kudlur, M., Dumoulin, V., Shlens, J.: Exploring the structure of a real-time, arbitrary neural artistic stylization network. CoRR abs\/1705.06830 (2017)","DOI":"10.5244\/C.31.114"},{"key":"32_CR11","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 2006, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"issue":"8","key":"32_CR12","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.J.: Arbitrary style transfer in real-time with adaptive instance normalization. CoRR abs\/1703.06868 (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"32_CR14","unstructured":"Kang, L., Rusi\u00f1ol, M., Forn\u00e9s, A., Riba, P., Villegas, M.: Unsupervised writer adaptation for synthetic-to-real handwritten word recognition. CoRR abs\/1909.08473 (2019)"},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. CoRR abs\/1812.04948 (2018)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Kim, T., Song, I., Bengio, Y.: Dynamic layer normalization for adaptive neural acoustic modeling in speech recognition. CoRR abs\/1707.06065 (2017)","DOI":"10.21437\/Interspeech.2017-556"},{"key":"32_CR17","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Conference Track Proceedings (2015)"},{"key":"32_CR18","doi-asserted-by":"crossref","unstructured":"Kodym, O., Hradi\u0161, M.: Page layout analysis system for unconstrained historic documents (2021)","DOI":"10.1007\/978-3-030-86331-9_32"},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Li, B., Sim, K.C.: Comparison of discriminative input and output transformations for speaker adaptation in the hybrid NN\/HMM systems. In: Eleventh Annual Conference of the International Speech Communication Association (2010)","DOI":"10.21437\/Interspeech.2010-214"},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Mana, F., Weninger, F., Gemello, R., Zhan, P.: Online batch normalization adaptation for automatic speech recognition. In: IEEE ASRU 2019, pp. 875\u2013880. IEEE (2019)","DOI":"10.1109\/ASRU46091.2019.9003883"},{"key":"32_CR21","doi-asserted-by":"crossref","unstructured":"Michael, J., Labahn, R., Gr\u00fcning, T., Z\u00f6llner, J.: Evaluating sequence-to-sequence models for handwritten text recognition. In: ICDAR 2019, Sydney, Australia, 20\u201325 September 2019, pp. 1286\u20131293. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00208"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Mohamed, A.R., Hinton, G., Penn, G.: Understanding how deep belief networks perform acoustic modelling. In: IEEE ICASSP 2012, pp. 4273\u20134276. IEEE (2012)","DOI":"10.1109\/ICASSP.2012.6288863"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Neto, J., et al.: Speaker-adaptation for hybrid HMM-ANN continuous speech recognition system (1995)","DOI":"10.21437\/Eurospeech.1995-411"},{"key":"32_CR24","doi-asserted-by":"crossref","unstructured":"Papadopoulos, C., Pletschacher, S., Clausner, C., Antonacopoulos, A.: The impact dataset of historical document images. In: Proceedings of the 2nd International Workshop on Historical Document Imaging and Processing, pp. 123\u2013130 (2013)","DOI":"10.1145\/2501115.2501130"},{"key":"32_CR25","doi-asserted-by":"crossref","unstructured":"Puigcerver, J.: Are multidimensional recurrent layers really necessary for handwritten text recognition? In: ICDAR 2017, vol. 01, pp. 67\u201372 (2017)","DOI":"10.1109\/ICDAR.2017.20"},{"issue":"12","key":"32_CR26","doi-asserted-by":"publisher","first-page":"2241","DOI":"10.1109\/TASLP.2016.2601146","volume":"24","author":"L Samarakoon","year":"2016","unstructured":"Samarakoon, L., Sim, K.C.: Factorized hidden layer adaptation for deep neural network based acoustic modeling. IEEE\/ACM Trans. Audio Speech Lang. Process. 24(12), 2241\u20132250 (2016)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"32_CR27","unstructured":"Sar\u0131, L., Thomas, S., Hasegawa-Johnson, M., Picheny, M.: Speaker adaptation of neural networks with learning speaker aware offsets. Interspeech (2019)"},{"key":"32_CR28","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. CoRR abs\/1507.05717 (2015)"},{"key":"32_CR29","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"32_CR30","unstructured":"Singh, S., Krishnan, S.: Filter response normalization layer: eliminating batch dependence in the training of deep neural networks. CoRR abs\/1911.09737 (2019)"},{"key":"32_CR31","doi-asserted-by":"crossref","unstructured":"Soullard, Y., Swaileh, W., Tranouez, P., Paquet, T., Chatelain, C.: Improving text recognition using optical and language model writer adaptation. In: ICDAR 2019, pp. 1175\u20131180 (2019)","DOI":"10.1109\/ICDAR.2019.00190"},{"key":"32_CR32","unstructured":"Swietojanski, P., Li, J., Renals, S.: Learning hidden unit contributions for unsupervised acoustic model adaptation. CoRR abs\/1601.02828 (2016)"},{"key":"32_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Z.Q., Wang, D.: Unsupervised speaker adaptation of batch normalized acoustic models for robust ASR. In: IEEE ICASSP 2017, pp. 4890\u20134894. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7953086"},{"key":"32_CR34","doi-asserted-by":"crossref","unstructured":"Xie, X., Liu, X., Lee, T., Wang, L.: Fast DNN acoustic model speaker adaptation by learning hidden unit contribution features. In: INTERSPEECH, pp. 759\u2013763 (2019)","DOI":"10.21437\/Interspeech.2019-2050"},{"key":"32_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, C., Woodland, P.C.: Parameterised sigmoid and ReLU hidden activation functions for DNN acoustic modelling. In: Sixteenth Annual Conference of the International Speech Communication Association (2015)","DOI":"10.21437\/Interspeech.2015-649"},{"key":"32_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Nie, S., Liu, W., Xu, X., Zhang, D., Shen, H.T.: Sequence-to-sequence domain adaptation network for robust text image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2740\u20132749 (2019)","DOI":"10.1109\/CVPR.2019.00285"},{"key":"32_CR37","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Li, J., Gong, Y.: Low-rank plus diagonal adaptation for deep neural networks. In: IEEE ICASSP 2016, pp. 5005\u20135009. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472630"},{"key":"32_CR38","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Li, J., Kumar, K., Gong, Y.: Extended low-rank plus diagonal adaptation for deep and recurrent neural networks. In: IEEE ICASSP 2017, pp. 5040\u20135044. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7953116"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86337-1_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T22:12:09Z","timestamp":1756851129000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86337-1_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863364","9783030863371"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86337-1_32","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":"2 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lausanne","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","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":"5 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iapr.org\/icdar2021","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":"340","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":"182","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":"54% - 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":"2.9","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":"4.9","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Additionally, 13 competition reports are included.","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)"}}]}}