{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T14:52:13Z","timestamp":1750863133343,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030863395"},{"type":"electronic","value":"9783030863401"}],"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\/978-3-030-86340-1_48","type":"book-chapter","created":{"date-parts":[[2021,9,10]],"date-time":"2021-09-10T12:03:14Z","timestamp":1631275394000},"page":"599-610","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["PhonicsGAN: Synthesizing Graphical Videos from Phonics Songs"],"prefix":"10.1007","author":[{"given":"Nuha","family":"Aldausari","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arcot","family":"Sowmya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nadine","family":"Marcus","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gelareh","family":"Mohammadi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,7]]},"reference":[{"key":"48_CR1","unstructured":"https:\/\/cloud.google.com\/speech-to-text"},{"issue":"2","key":"48_CR2","doi-asserted-by":"publisher","first-page":"3500","DOI":"10.1109\/LRA.2020.2977333","volume":"5","author":"H Ahn","year":"2020","unstructured":"Ahn, H., Kim, J., et al.: Generative autoregressive networks for 3D dancing move synthesis from music. IEEE Robot. Autom. Lett. 5(2), 3500\u20133507 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"48_CR3","unstructured":"Aifanti, N., Papachristou, C., et al.: The mug facial expression database. In: 11th International Workshop on Image Analysis for Multimedia Interactive Services WIAMIS 2010, pp. 1\u20134. IEEE (2010)"},{"key":"48_CR4","unstructured":"Aldausari, N., Sowmya, A., et al.: Video generative adversarial networks: a review. arXiv preprint arXiv:2011.02250 (2020)"},{"key":"48_CR5","doi-asserted-by":"crossref","unstructured":"Chen, L., Srivastava, S., et al.: Deep cross-modal audio-visual generation. In: Proceedings of the on Thematic Workshops of ACM Multimedia 2017, pp. 349\u2013357. ACM (2017)","DOI":"10.1145\/3126686.3126723"},{"key":"48_CR6","unstructured":"CISCO: VNI complete forecast highlights. Report shorturl.at\/tDGV2"},{"key":"48_CR7","unstructured":"Duan, B., Wang, W., et al.: Cascade attention guided residue learning gan for cross-modal translation. arXiv preprint arXiv:1907.01826 (2019)"},{"key":"48_CR8","unstructured":"Duan, Y., Shi, T., et al.: Semi-supervised learning for in-game expert-level music-to-dance translation. arXiv preprint arXiv:2009.12763 (2020)"},{"key":"48_CR9","unstructured":"Goodfellow, I., Pouget-Abadie, J., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"48_CR10","unstructured":"Heusel, M., Ramsauer, H., et al.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems, pp. 6626\u20136637 (2017)"},{"key":"48_CR11","unstructured":"Kaneko, T., Takaki, S., et al.: Generative adversarial network-based postfilter for STFT spectrograms. In: Interspeech, pp. 3389\u20133393"},{"key":"48_CR12","unstructured":"Karras, T., Aila, T., et al.: Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017)"},{"key":"48_CR13","doi-asserted-by":"crossref","unstructured":"Kim, K.M., Heo, M.O., et al.: Deepstory: video story QA by deep embedded memory networks. arXiv preprint arXiv:1707.00836 (2017)","DOI":"10.24963\/ijcai.2017\/280"},{"key":"48_CR14","unstructured":"Lee, H.Y., Yang, X., et al.: Dancing to music. arXiv preprint arXiv:1911.02001 (2019)"},{"key":"48_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., Gan, Z., et al.: StoryGAN: a sequential conditional GAN for story visualization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6329\u20136338 (2019)","DOI":"10.1109\/CVPR.2019.00649"},{"key":"48_CR16","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"48_CR17","doi-asserted-by":"crossref","unstructured":"Mittal, G., Wang, B.: Animating face using disentangled audio representations. In: The IEEE Winter Conference on Applications of Computer Vision, pp. 3290\u20133298 (2019)","DOI":"10.1109\/WACV45572.2020.9093527"},{"key":"48_CR18","unstructured":"van den Oord, A., Dieleman, S., Zen, H., et al.: WaveNet: a generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016)"},{"key":"48_CR19","unstructured":"Qiu, Y., Kataoka, H.: Image generation associated with music data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 2510\u20132513 (2018)"},{"key":"48_CR20","doi-asserted-by":"crossref","unstructured":"Ren, X., Li, H., et al.: Self-supervised dance video synthesis conditioned on music. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 46\u201354 (2020)","DOI":"10.1145\/3394171.3413932"},{"key":"48_CR21","unstructured":"R\u00f6ssler, A., Cozzolino, D., et al.: FaceForensics: a large-scale video dataset for forgery detection in human faces. arXiv preprint arXiv:1803.09179 (2018)"},{"key":"48_CR22","unstructured":"Salimans, T., Goodfellow, I., et al.: Improved techniques for training GANs. arXiv preprint arXiv:1606.03498 (2016)"},{"key":"48_CR23","doi-asserted-by":"crossref","unstructured":"Schuldt, C., Laptev, I., et al.: Recognizing human actions: a local SVM approach. In: Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004, vol. 3, pp. 32\u201336. IEEE (2004)","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"48_CR24","unstructured":"Soomro, K., Zamir, A.R., et al.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"48_CR25","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1109\/TMM.2020.2981989","volume":"23","author":"G Sun","year":"2020","unstructured":"Sun, G., Wong, Y., et al.: DeepDance: music-to-dance motion choreography with adversarial learning. IEEE Trans. Multimed. 23, 497\u2013509 (2020)","journal-title":"IEEE Trans. Multimed."},{"key":"48_CR26","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"48_CR27","doi-asserted-by":"crossref","unstructured":"Tang, T., Jia, J., et al.: Dance with melody: an LSTM-autoencoder approach to music-oriented dance synthesis. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 1598\u20131606 (2018)","DOI":"10.1145\/3240508.3240526"},{"key":"48_CR28","unstructured":"Tsuchiya, Y., Itazuri, T., et al.: Generating video from single image and sound. In: CVPR Workshops, pp. 17\u201320 (2019)"},{"key":"48_CR29","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Liu, M.Y., et al.: MoCoGAN: decomposing motion and content for video generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1526\u20131535 (2017)","DOI":"10.1109\/CVPR.2018.00165"},{"key":"48_CR30","unstructured":"Vougioukas, K., Petridis, S., et al.: End-to-end speech-driven facial animation with temporal GANs. arXiv preprint arXiv:1805.09313 (2018)"},{"key":"48_CR31","unstructured":"Wang, T.C., Liu, M.Y., et al.: Video-to-video synthesis. arXiv preprint arXiv:1808.06601 (2018)"},{"key":"48_CR32","doi-asserted-by":"crossref","unstructured":"Wang, Y., Skerry-Ryan, R., et al.: Tacotron: towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135 (2017)","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"48_CR33","doi-asserted-by":"crossref","unstructured":"Yalta, N., Watanabe, S., et al.: Weakly-supervised deep recurrent neural networks for basic dance step generation. In: 2019 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2019)","DOI":"10.1109\/IJCNN.2019.8851872"},{"key":"48_CR34","doi-asserted-by":"crossref","unstructured":"Yang, Z., Zhu, W., et al.: TransMoMo: invariance-driven unsupervised video motion retargeting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5306\u20135315 (2020)","DOI":"10.1109\/CVPR42600.2020.00535"},{"key":"48_CR35","doi-asserted-by":"crossref","unstructured":"Zhou, H., Liu, Y., et al.: Talking face generation by adversarially disentangled audio-visual representation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 9299\u20139306 (2019)","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"48_CR36","unstructured":"Zhuang, W., Wang, C., et al.: Music2dance: music-driven dance generation using Wavenet. arXiv preprint arXiv:2002.03761 (2020)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86340-1_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,10]],"date-time":"2021-09-10T12:16:30Z","timestamp":1631276190000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86340-1_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863395","9783030863401"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86340-1_48","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":"7 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bratislava","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovakia","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 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2021","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":"icann2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2021\/","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":"OCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"496","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":"265","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":"4","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":"53% - 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":"2.5","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":"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)"}}]}}