{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T16:56:52Z","timestamp":1758473812445,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031439896"},{"type":"electronic","value":"9783031439902"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-43990-2_41","type":"book-chapter","created":{"date-parts":[[2023,9,30]],"date-time":"2023-09-30T23:07:48Z","timestamp":1696115268000},"page":"435-445","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Speech Audio Synthesis from\u00a0Tagged MRI and\u00a0Non-negative Matrix Factorization via\u00a0Plastic Transformer"],"prefix":"10.1007","author":[{"given":"Xiaofeng","family":"Liu","sequence":"first","affiliation":[]},{"given":"Fangxu","family":"Xing","sequence":"additional","affiliation":[]},{"given":"Maureen","family":"Stone","sequence":"additional","affiliation":[]},{"given":"Jiachen","family":"Zhuo","sequence":"additional","affiliation":[]},{"given":"Sidney","family":"Fels","sequence":"additional","affiliation":[]},{"given":"Jerry L.","family":"Prince","sequence":"additional","affiliation":[]},{"given":"Georges","family":"El Fakhri","sequence":"additional","affiliation":[]},{"given":"Jonghye","family":"Woo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,1]]},"reference":[{"key":"41_CR1","doi-asserted-by":"crossref","unstructured":"Akbari, H., Arora, H., Cao, L., Mesgarani, N.: Lip2audspec: speech reconstruction from silent lip movements video. In: ICASSP, pp. 2516\u20132520. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461856"},{"issue":"11","key":"41_CR2","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00021","volume":"4","author":"A Araujo","year":"2019","unstructured":"Araujo, A., Norris, W., Sim, J.: Computing receptive fields of convolutional neural networks. Distill 4(11), e21 (2019)","journal-title":"Distill"},{"key":"41_CR3","doi-asserted-by":"crossref","unstructured":"Che, T., et al.: Deep verifier networks: verification of deep discriminative models with deep generative models. In: AAAI (2021)","DOI":"10.1609\/aaai.v35i8.16862"},{"issue":"2","key":"41_CR4","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1121\/1.1945807","volume":"118","author":"T Chi","year":"2005","unstructured":"Chi, T., Ru, P., Shamma, S.A.: Multiresolution spectrotemporal analysis of complex sounds. J. Acoust. Soc. Am. 118(2), 887\u2013906 (2005)","journal-title":"J. Acoust. Soc. Am."},{"key":"41_CR5","first-page":"9355","volume":"34","author":"X Chu","year":"2021","unstructured":"Chu, X., et al.: Twins: revisiting the design of spatial attention in vision transformers. Adv. Neural. Inf. Process. Syst. 34, 9355\u20139366 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"41_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-319-54184-6_6","volume-title":"Computer Vision \u2013 ACCV 2016","author":"JS Chung","year":"2017","unstructured":"Chung, J.S., Zisserman, A.: Lip reading in the wild. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10112, pp. 87\u2013103. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54184-6_6"},{"key":"41_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"41_CR8","unstructured":"Dziugaite, G.K., Roy, D.M., Ghahramani, Z.: Training generative neural networks via maximum mean discrepancy optimization. arXiv preprint arXiv:1505.03906 (2015)"},{"key":"41_CR9","doi-asserted-by":"crossref","unstructured":"Ephrat, A., Peleg, S.: Vid2speech: speech reconstruction from silent video. In: ICASSP, pp. 5095\u20135099. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7953127"},{"issue":"11","key":"41_CR10","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"issue":"2","key":"41_CR11","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1109\/TASSP.1984.1164317","volume":"32","author":"D Griffin","year":"1984","unstructured":"Griffin, D., Lim, J.: Signal estimation from modified short-time Fourier transform. IEEE Trans. Acoust. Speech Signal Process. 32(2), 236\u2013243 (1984)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"41_CR12","doi-asserted-by":"crossref","unstructured":"He, G., Liu, X., Fan, F., You, J.: Image2audio: facilitating semi-supervised audio emotion recognition with facial expression image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 912\u2013913 (2020)","DOI":"10.1109\/CVPRW50498.2020.00464"},{"issue":"9","key":"41_CR13","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"41_CR14","unstructured":"Huang, T., Huang, L., You, S., Wang, F., Qian, C., Xu, C.: Lightvit: towards light-weight convolution-free vision transformers. arXiv preprint arXiv:2207.05557 (2022)"},{"key":"41_CR15","doi-asserted-by":"crossref","unstructured":"Lee, J., Woo, J., Xing, F., Murano, E.Z., Stone, M., Prince, J.L.: Semi-automatic segmentation of the tongue for 3D motion analysis with dynamic MRI. In: ISBI, pp. 1465\u20131468. IEEE (2013)","DOI":"10.1109\/ISBI.2013.6556811"},{"key":"41_CR16","first-page":"5243","volume":"44","author":"X Liu","year":"2021","unstructured":"Liu, X., Chao, Y., You, J.J., Kuo, C.C.J., Vijayakumar, B.: Mutual information regularized feature-level Frankenstein for discriminative recognition. IEEE TPAMI 44, 5243\u20135260 (2021)","journal-title":"IEEE TPAMI"},{"key":"41_CR17","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: Domain generalization under conditional and label shifts via variational Bayesian inference. IJCAI (2021)","DOI":"10.24963\/ijcai.2021\/122"},{"key":"41_CR18","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: Feature-level Frankenstein: eliminating variations for discriminative recognition. In: CVPR, pp. 637\u2013646 (2019)","DOI":"10.1109\/CVPR.2019.00073"},{"key":"41_CR19","doi-asserted-by":"crossref","unstructured":"Liu, X., Vijaya Kumar, B., You, J., Jia, P.: Adaptive deep metric learning for identity-aware facial expression recognition. In: CVPR, pp. 20\u201329 (2017)","DOI":"10.1109\/CVPRW.2017.79"},{"key":"41_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"41_CR21","unstructured":"Luo, W., Li, Y., Urtasun, R., Zemel, R.: Understanding the effective receptive field in deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"41_CR22","unstructured":"Recommendation, I.T.: Perceptual evaluation of speech quality PESQ): an objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs. Rec. ITU-T P. 862 (2001)"},{"key":"41_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/978-3-030-86340-1_11","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2021","author":"ML Richter","year":"2021","unstructured":"Richter, M.L., Byttner, W., Krumnack, U., Wiedenroth, A., Schallner, L., Shenk, J.: (Input) size matters for CNN classifiers. In: Farka\u0161, I., Masulli, P., Otte, S., Wermter, S. (eds.) ICANN 2021. LNCS, vol. 12892, pp. 133\u2013144. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86340-1_11"},{"key":"41_CR24","first-page":"2234","volume":"29","author":"T Salimans","year":"2016","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. NIPS 29, 2234\u20132242 (2016)","journal-title":"NIPS"},{"issue":"3","key":"41_CR25","doi-asserted-by":"publisher","first-page":"730","DOI":"10.1109\/TMI.2018.2870939","volume":"38","author":"J Woo","year":"2018","unstructured":"Woo, J., et al.: A sparse non-negative matrix factorization framework for identifying functional units of tongue behavior from MRI. IEEE Trans. Med. Imaging 38(3), 730\u2013740 (2018)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"41_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102131","volume":"72","author":"J Woo","year":"2021","unstructured":"Woo, J., et al.: A deep joint sparse non-negative matrix factorization framework for identifying the common and subject-specific functional units of tongue motion during speech. Med. Image Anal. 72, 102131 (2021)","journal-title":"Med. Image Anal."},{"key":"41_CR27","doi-asserted-by":"crossref","unstructured":"Woo, J., et al.: Identifying the common and subject-specific functional units of speech movements via a joint sparse non-negative matrix factorization framework. In: Medical Imaging 2020: Image Processing, vol. 11313, pp. 446\u2013451. SPIE (2020)","DOI":"10.1117\/12.2548991"},{"key":"41_CR28","doi-asserted-by":"crossref","unstructured":"Wu, K., Peng, H., Chen, M., Fu, J., Chao, H.: Rethinking and improving relative position encoding for vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10033\u201310041 (2021)","DOI":"10.1109\/ICCV48922.2021.00988"},{"issue":"10","key":"41_CR29","first-page":"2116","volume":"36","author":"F Xing","year":"2017","unstructured":"Xing, F., et al.: Phase vector incompressible registration algorithm for motion estimation from tagged magnetic resonance images. IEEE TMI 36(10), 2116\u20132128 (2017)","journal-title":"IEEE TMI"},{"key":"41_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1007\/978-3-642-40760-4_6","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2013","author":"F Xing","year":"2013","unstructured":"Xing, F., Woo, J., Murano, E.Z., Lee, J., Stone, M., Prince, J.L.: 3D tongue motion from tagged and cine MR images. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013. LNCS, vol. 8151, pp. 41\u201348. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-40760-4_6"},{"key":"41_CR31","unstructured":"Yang, J., et al.: Focal self-attention for local-global interactions in vision transformers. arXiv preprint arXiv:2107.00641 (2021)"},{"key":"41_CR32","first-page":"15475","volume":"34","author":"Q Zhang","year":"2021","unstructured":"Zhang, Q., Yang, Y.B.: Rest: an efficient transformer for visual recognition. Adv. Neural. Inf. Process. Syst. 34, 15475\u201315485 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43990-2_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,11]],"date-time":"2024-03-11T15:40:24Z","timestamp":1710171624000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43990-2_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031439896","9783031439902"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43990-2_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vancouver, BC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","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":"8 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2023\/en\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2250","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":"730","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":"32% - 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)"}}]}}