{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T08:12:30Z","timestamp":1743149550437,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030377304"},{"type":"electronic","value":"9783030377311"}],"license":[{"start":{"date-parts":[[2019,12,24]],"date-time":"2019-12-24T00:00:00Z","timestamp":1577145600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-37731-1_49","type":"book-chapter","created":{"date-parts":[[2019,12,27]],"date-time":"2019-12-27T01:02:51Z","timestamp":1577408571000},"page":"605-616","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["HRTF Representation with Convolutional Auto-encoder"],"prefix":"10.1007","author":[{"given":"Wei","family":"Chen","sequence":"first","affiliation":[]},{"given":"Ruimin","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Xiaochen","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Dengshi","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,12,24]]},"reference":[{"key":"49_CR1","unstructured":"Ari hrtf database homepage. \nhttp:\/\/www.kfs.oeaw.ac.at\/hrtf\n\n. Accessed 4 July 2019"},{"issue":"4","key":"49_CR2","doi-asserted-by":"publisher","first-page":"2456","DOI":"10.1121\/1.4964753","volume":"140","author":"R Baumgartner","year":"2016","unstructured":"Baumgartner, R., Majdak, P., Laback, B.: Modeling sound-source localization in sagittal planes for human listeners. J. Acoust. Soc. Am. 140(4), 2456 (2016). \nhttps:\/\/doi.org\/10.1121\/1.4964753","journal-title":"J. Acoust. Soc. Am."},{"issue":"3","key":"49_CR3","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1109\/89.568734","volume":"5","author":"M Blommer","year":"1997","unstructured":"Blommer, M., Wakefield, G.: Pole-zero approximations for head-related transfer functions using a logarithmic error criterion. IEEE Trans. Speech Audio Process. 5(3), 278\u2013287 (1997)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"49_CR4","unstructured":"Chen, M.C., Hsieh, S.F.: Common acoustical-poles\/zeros modeling for 3D sound processing. In: Proceedings of the 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 785\u2013788. IEEE Signal Processing Society (2000)"},{"key":"49_CR5","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1016\/j.apacoust.2014.07.005","volume":"87","author":"KJ Fink","year":"2015","unstructured":"Fink, K.J., Ray, L.: Individualization of head related transfer functions using principal component analysis. Appl. Acoust. 87, 162\u2013173 (2015)","journal-title":"Appl. Acoust."},{"key":"49_CR6","doi-asserted-by":"publisher","unstructured":"Grais, E.M., Plumbley, M.D.: Single channel audio source separation using convolutional denoising autoencoders. In: 2017 IEEE Global Conference on Signal and Information Processing (GLOBALSIP 2017), pp. 1265\u20131269. IEEE (2017). \nhttps:\/\/doi.org\/10.1109\/GlobalSIP.2017.8309164","DOI":"10.1109\/GlobalSIP.2017.8309164"},{"issue":"3","key":"49_CR7","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1109\/TASLP.2016.2517565","volume":"24","author":"F Grijalva","year":"2016","unstructured":"Grijalva, F., Martini, L., Florencio, D., Goldenstein, S.: A manifold learning approach for personalizing HRTFs from anthropometric features. IEEE\/ACM Trans. Audio Speech Lang. Process. 24(3), 559\u2013570 (2016)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"2","key":"49_CR8","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/LSP.2017.2648794","volume":"24","author":"F Grijalva","year":"2017","unstructured":"Grijalva, F., Martini, L.C., Florencio, D., Goldenstein, S.: Interpolation of head-related transfer functions using manifold learning. IEEE Signal Process. Lett. 24(2), 221\u2013225 (2017)","journal-title":"IEEE Signal Process. Lett."},{"key":"49_CR9","doi-asserted-by":"publisher","first-page":"24829","DOI":"10.1109\/ACCESS.2018.2832645","volume":"6","author":"F Grijalva","year":"2018","unstructured":"Grijalva, F., Martini, L.C., Masiero, B., Goldenstein, S.: A recommender system for improving median plane sound localization performance based on a nonlinear representation of HRTFs. IEEE Access 6, 24829\u201324836 (2018)","journal-title":"IEEE Access"},{"issue":"2","key":"49_CR10","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1109\/89.748123","volume":"7","author":"Y Haneda","year":"1999","unstructured":"Haneda, Y., Makino, S., Kaneda, Y., Kitawaki, N.: Common-acoustical-pole and zero modeling of head-related transfer functions. IEEE Trans. Speech Audio Process. 7(2), 188\u2013196 (1999)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"49_CR11","unstructured":"Hugeng, Gunawan, D., Wahab, W.: Effective preprocessing in modeling head-related impulse responses based on principal components analysis. Sig. Process. Int. J. 4(4), 201\u2013212 (2010)"},{"key":"49_CR12","unstructured":"Iwaya, Y., Sato, W., Okamoto, T., Otani, M., Suzuki, Y.: Interpolation method of head-related transfer functions in the z-plane domain using a common-pole and zero model. In: 20th International Congress on Acoustics 2010, ICA 2010, Sydney, NSW, Australia, vol. 4, pp. 2936\u20132940 (2010)"},{"issue":"3","key":"49_CR13","doi-asserted-by":"publisher","first-page":"1637","DOI":"10.1121\/1.402444","volume":"91","author":"DJ Kistler","year":"1992","unstructured":"Kistler, D.J., Wightman, F.L.: A model of head-related transfer-functions based on principal components-analysis and minimum-phase reconstruction. J. Acoust. Soc. Am. 91(3), 1637\u20131647 (1992)","journal-title":"J. Acoust. Soc. Am."},{"key":"49_CR14","doi-asserted-by":"publisher","first-page":"1714","DOI":"10.1121\/1.1650332","volume":"115","author":"A Kulkarni","year":"2004","unstructured":"Kulkarni, A., Colburn, H.S.: Infinite-impulse-response models of the head-related transfer function. J. Acoust. Soc. Am. 115, 1714\u20131728 (2004)","journal-title":"J. Acoust. Soc. Am."},{"key":"49_CR15","unstructured":"Liu, C.J., Hsieh, S.F.: Common-acoustic-poles\/zeros approximation of head-related transfer functions. In: 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 3341\u20133344. IEEE Signal Processing Society (2001)"},{"issue":"2","key":"49_CR16","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1109\/97.554467","volume":"4","author":"J Mackenzie","year":"1997","unstructured":"Mackenzie, J., Huopaniemi, J., Valimaki, V., Kale, I.: Low-order modeling of head-related transfer functions using balanced model truncation. IEEE Signal Process. Lett. 4(2), 39\u201341 (1997)","journal-title":"IEEE Signal Process. Lett."},{"issue":"2","key":"49_CR17","doi-asserted-by":"publisher","first-page":"454","DOI":"10.3758\/APP.72.2.454","volume":"72","author":"P Majdak","year":"2010","unstructured":"Majdak, P., Goupell, M.J., Laback, B.: 3-D localization of virtual sound sources: effects of visual environment, pointing method, and training. Atten. Percept. Psychophys. 72(2), 454\u2013469 (2010)","journal-title":"Atten. Percept. Psychophys."},{"key":"49_CR18","unstructured":"Martens, W.L.: Principal components analysis and resynthesis of spectral cues to perceived direction. In: Proceedings of the International Computer Music Conference, Champaine-Urbana, IL (1987)"},{"key":"49_CR19","doi-asserted-by":"publisher","unstructured":"Meng, L., Wang, X., Chen, W., Ai, C., Hu, R.: Individualization of head related transfer functions based on radial basis function neural network. In: 2018 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136 (2018). \nhttps:\/\/doi.org\/10.1109\/ICME.2018.8486494","DOI":"10.1109\/ICME.2018.8486494"},{"issue":"3","key":"49_CR20","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1121\/1.427176","volume":"106","author":"JC Middlebrooks","year":"1999","unstructured":"Middlebrooks, J.C.: Individual differences in external-ear transfer functions reduced by scaling in frequency. J. Acoust. Soc. Am. 106(3), 1480\u20131492 (1999)","journal-title":"J. Acoust. Soc. Am."},{"key":"49_CR21","series-title":"Advances in Intelligent Systems and Computing","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-319-65978-7_16","volume-title":"Recent Developments in Mechatronics and Intelligent Robotics","author":"X Ming","year":"2018","unstructured":"Ming, X., Binzhou, Y., Shuxia, G., Ying, G.: Head-related transfer function individualization based on locally linear embedding. In: Qiao, F., Patnaik, S., Wang, J. (eds.) ICMIR 2017. AISC, vol. 690, pp. 104\u2013111. Springer, Cham (2018). \nhttps:\/\/doi.org\/10.1007\/978-3-319-65978-7_16"},{"key":"49_CR22","unstructured":"Turchenko, V., Chalmers, E., Luczak, A.: A deep convolutional auto-encoder with pooling \u2013 unpooling layers in caffe. Int. J. Comput. 18(1), 8\u201331 (2019). \nhttp:\/\/www.computingonline.net\/computing\/article\/view\/1270"},{"key":"49_CR23","first-page":"3371","volume":"11","author":"P Vincent","year":"2010","unstructured":"Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., Manzagol, P.A.: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion. J. Mach. Learn. Res. 11, 3371\u20133408 (2010)","journal-title":"J. Mach. Learn. Res."},{"key":"49_CR24","doi-asserted-by":"publisher","unstructured":"Zeiler, M.D., Krishnan, D., Taylor, G.W., Fergus, R.: Deconvolutional networks. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2528\u20132535. IEEE Computer Society (2010). \nhttps:\/\/doi.org\/10.1109\/CVPR.2010.5539957","DOI":"10.1109\/CVPR.2010.5539957"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-37731-1_49","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,6]],"date-time":"2020-02-06T11:23:04Z","timestamp":1580988184000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-37731-1_49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,24]]},"ISBN":["9783030377304","9783030377311"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-37731-1_49","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019,12,24]]},"assertion":[{"value":"24 December 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 January 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 January 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.mmm2020.kr\/","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":"171","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":"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":"23% - 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)"}},{"value":"Of the 171 submissions, 46 were accepted as poster papers; of the 49 special session paper submissions, 28 were accepted for oral presentation and 8 for poster presentation; 9 demo papers and 10 VBS papers were also accepted.","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)"}}]}}