{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T01:36:27Z","timestamp":1743125787478,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031164453"},{"type":"electronic","value":"9783031164460"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-16446-0_36","type":"book-chapter","created":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T09:02:47Z","timestamp":1663318967000},"page":"376-386","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Tagged-MRI Sequence to\u00a0Audio Synthesis via\u00a0Self Residual Attention Guided Heterogeneous Translator"],"prefix":"10.1007","author":[{"given":"Xiaofeng","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangxu","family":"Xing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jerry L.","family":"Prince","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiachen","family":"Zhuo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maureen","family":"Stone","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georges","family":"El Fakhri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonghye","family":"Woo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,9,17]]},"reference":[{"key":"36_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"},{"key":"36_CR2","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":"36_CR3","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":"36_CR4","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":"36_CR5","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"},{"key":"36_CR6","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning (adaptive Computation And Machine Learning Series). MIT Press, Cambridge (2017)"},{"issue":"2","key":"36_CR7","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":"36_CR8","doi-asserted-by":"crossref","unstructured":"He, G., Liu, X., Fan, F., You, J.: Classification-aware semi-supervised domain adaptation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 964\u2013965 (2020)","DOI":"10.1109\/CVPRW50498.2020.00490"},{"key":"36_CR9","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"},{"key":"36_CR10","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":"36_CR11","doi-asserted-by":"crossref","unstructured":"Liu, X., Chao, Y., You, J.J., Kuo, C.C.J., Vijayakumar, B.: Mutual information regularized feature-level Frankenstein for discriminative recognition. In: IEEE TPAMI (2021)","DOI":"10.1109\/TPAMI.2021.3077397"},{"key":"36_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1007\/978-3-030-58545-7_4","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Liu","year":"2020","unstructured":"Liu, X., Che, T., Lu, Y., Yang, C., Li, S., You, J.: AUTO3D: novel view synthesis through unsupervisely learned variational viewpoint and global 3D representation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 52\u201371. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_4"},{"key":"36_CR13","doi-asserted-by":"publisher","first-page":"1501","DOI":"10.1109\/TIFS.2019.2938418","volume":"15","author":"X Liu","year":"2019","unstructured":"Liu, X., Guo, Z., You, J., Kumar, B.V.: Dependency-aware attention control for image set-based face recognition. IEEE Trans. Inf. Forensic. Secur. 15, 1501\u20131512 (2019)","journal-title":"IEEE Trans. Inf. Forensic. Secur."},{"key":"36_CR14","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: Domain generalization under conditional and label shifts via variational Bayesian inference. In: IJCAI (2021)","DOI":"10.24963\/ijcai.2021\/122"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Liu, X., Li, S., Kong, L., Xie, W., Jia, P., You, J., Kumar, B.: Feature-level Frankenstein: Eliminating variations for discriminative recognition. In: CVPR, pp. 637\u2013646 (2019)","DOI":"10.1109\/CVPR.2019.00073"},{"key":"36_CR16","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":"36_CR17","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: Dual-cycle constrained bijective VAE-GAN for tagged-to-cine magnetic resonance image synthesis. In: ISBI, pp. 1448\u20131452. IEEE (2021)","DOI":"10.1109\/ISBI48211.2021.9433852"},{"key":"36_CR18","doi-asserted-by":"crossref","unstructured":"Liu, X., Xing, F., Prince, J.L., Stone, M., El Fakhri, G., Woo, J.: Structure-aware unsupervised tagged-to-cine MRI synthesis with self disentanglement. In: Medical Imaging 2022: Image Processing, vol. 12032, pp. 470\u2013476. SPIE (2022)","DOI":"10.1117\/12.2610655"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: CMRI2spec: Cine MRI sequence to spectrogram synthesis via a pairwise heterogeneous translator. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1481\u20131485. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9746381"},{"issue":"4","key":"36_CR20","doi-asserted-by":"publisher","first-page":"A133","DOI":"10.1121\/10.0010891","volume":"151","author":"X Liu","year":"2022","unstructured":"Liu, X., et al.: Tagged-MRI to audio synthesis with a pairwise heterogeneous deep translator. J. Acoust. Soc. Am. 151(4), A133\u2013A133 (2022)","journal-title":"J. Acoust. Soc. Am."},{"key":"36_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1007\/978-3-030-87199-4_13","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"X Liu","year":"2021","unstructured":"Liu, X., et al.: Generative self-training for cross-domain unsupervised tagged-to-cine MRI synthesis. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12903, pp. 138\u2013148. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87199-4_13"},{"key":"36_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1007\/978-3-030-72084-1_8","volume-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries","author":"X Liu","year":"2021","unstructured":"Liu, X., et al.: Symmetric-constrained irregular structure inpainting for brain MRI registration with tumor pathology. In: Crimi, A., Bakas, S. (eds.) BrainLes 2020. LNCS, vol. 12658, pp. 80\u201391. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-72084-1_8"},{"key":"36_CR23","doi-asserted-by":"publisher","first-page":"1368","DOI":"10.1109\/TASLP.2021.3066303","volume":"29","author":"D Michelsanti","year":"2021","unstructured":"Michelsanti, D., et al.: An overview of deep-learning-based audio-visual speech enhancement and separation. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 1368\u20131396 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"36_CR24","unstructured":"Pascanu, R., Mikolov, T., Bengio, Y.: On the difficulty of training recurrent neural networks. In: ICML, pp. 1310\u20131318. PMLR (2013)"},{"key":"36_CR25","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":"36_CR26","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"},{"key":"36_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101942","volume":"69","author":"J Wang","year":"2021","unstructured":"Wang, J., et al.: Automated interpretation of congenital heart disease from multi-view echocardiograms. Med. Image Anal. 69, 101942 (2021)","journal-title":"Med. Image Anal."},{"key":"36_CR28","doi-asserted-by":"crossref","unstructured":"Xie, W., Liang, L., Lu, Y., Luo, H., Liu, X.: Deep 3D-CNN for depression diagnosis with facial video recording of self-rating depression scale questionnaire. In: JBHI (2021)","DOI":"10.1109\/EMBC46164.2021.9630412"},{"key":"36_CR29","doi-asserted-by":"publisher","first-page":"3185","DOI":"10.1109\/JBHI.2022.3149754","volume":"26","author":"F Xing","year":"2022","unstructured":"Xing, F., Liu, X., Kuo, J., Fakhri, G., Woo, J.: Brain MR atlas construction using symmetric deep neural inpainting. IEEE J. Biomed. Health Inform. 26, 3185\u20133196 (2022)","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"36_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., et al.: 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":"36_CR31","doi-asserted-by":"crossref","unstructured":"Yu, Y., Shandiz, A.H., T\u00f3th, L.: Reconstructing speech from real-time articulatory MRI using neural vocoders. In: 2021 29th European Signal Processing Conference (EUSIPCO), pp. 945\u2013949. IEEE (2021)","DOI":"10.23919\/EUSIPCO54536.2021.9616153"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-16446-0_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T07:07:09Z","timestamp":1721372829000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16446-0_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031164453","9783031164460"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16446-0_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"17 September 2022","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":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2022\/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":"Microsoft Conference","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1831","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":"574","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":"31% - 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)"}}]}}