{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T17:53:24Z","timestamp":1758477204264,"version":"3.37.3"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2020,9,12]],"date-time":"2020-09-12T00:00:00Z","timestamp":1599868800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,9,12]],"date-time":"2020-09-12T00:00:00Z","timestamp":1599868800000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1007\/s11042-020-09735-3","type":"journal-article","created":{"date-parts":[[2020,9,12]],"date-time":"2020-09-12T15:02:39Z","timestamp":1599922959000},"page":"2205-2220","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Optimization of sound fields reproduction based Higher-Order Ambisonics (HOA) using the Generative Adversarial Network (GAN)"],"prefix":"10.1007","volume":"80","author":[{"given":"Lingkun","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1904-2097","authenticated-orcid":false,"given":"Xiaochen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruimin","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dengshi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weipin","family":"Tu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,9,12]]},"reference":[{"key":"9735_CR1","unstructured":"Abhayapala TD, Ward DB (2002) .. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, pp II\u20131949\u2013II\u20131952"},{"key":"9735_CR2","doi-asserted-by":"crossref","unstructured":"Ahrens J, Spors S (2008) .. In: 2008 IEEE international conference on acoustics, speech and signal processing, IEEE, pp 373\u2013376","DOI":"10.1109\/ICASSP.2008.4517624"},{"issue":"5","key":"9735_CR3","doi-asserted-by":"publisher","first-page":"2807","DOI":"10.1121\/1.3640850","volume":"130","author":"J Ahrens","year":"2011","unstructured":"Ahrens J, Spors S (2011) Wave field synthesis of moving virtual sound sources with complex radiation properties. The Journal of the Acoustical Society of America 130(5):2807","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"6","key":"9735_CR4","doi-asserted-by":"publisher","first-page":"1467","DOI":"10.1109\/TASL.2010.2092429","volume":"19","author":"A Ando","year":"2010","unstructured":"Ando A (2010) Conversion of multichannel sound signal maintaining physical properties of sound in reproduced sound field. IEEE Transactions on Audio, Speech, and Language Processing 19(6):1467","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9735_CR5","unstructured":"Ari hrtf database homepage. http:\/\/www.kfs.oeaw.ac.at\/hrtf. Last accessed 17 January 2020"},{"issue":"5","key":"9735_CR6","doi-asserted-by":"publisher","first-page":"2764","DOI":"10.1121\/1.405852","volume":"93","author":"AJ Berkhout","year":"1993","unstructured":"Berkhout AJ, de Vries D, Vogel P (1993) Acoustic control by wave field synthesis. The Journal of the Acoustical Society of America 93(5):2764","journal-title":"The Journal of the Acoustical Society of America"},{"key":"9735_CR7","doi-asserted-by":"crossref","unstructured":"Bi H, Li N, Guan H, Lu D, Yang L (2019) .. In: 2019 IEEE International Conference on Image Processing (ICIP), IEEE, pp 3876\u20133880","DOI":"10.1109\/ICIP.2019.8803629"},{"key":"9735_CR8","unstructured":"Bishop CM (2006) Pattern recognition and machine learning. Springer"},{"key":"9735_CR9","doi-asserted-by":"publisher","first-page":"48451","DOI":"10.1109\/ACCESS.2020.2979348","volume":"8","author":"W Cai","year":"2020","unstructured":"Cai W, Wei Z (2020) Piigan: Generative adversarial networks for pluralistic image inpainting. IEEE Access 8:48451","journal-title":"IEEE Access"},{"key":"9735_CR10","unstructured":"Chollet F et al (2015) Keras. https:\/\/github.com\/fchollet\/keras"},{"issue":"1","key":"9735_CR11","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/MSP.2017.2765202","volume":"35","author":"A Creswell","year":"2018","unstructured":"Creswell A, White T, Dumoulin V, Arulkumaran K, Sengupta B, Bharath AA (2018) Generative adversarial networks: an overview. IEEE Signal Proc Mag 35(1):53","journal-title":"IEEE Signal Proc Mag"},{"key":"9735_CR12","doi-asserted-by":"publisher","first-page":"105912","DOI":"10.1016\/j.asoc.2019.105912","volume":"86","author":"M Esmaeilpour","year":"2020","unstructured":"Esmaeilpour M, Cardinal P, Koerich AL (2020) Unsupervised feature learning for environmental sound classification using weighted cycle-consistent generative adversarial network. Appl Soft Comput 86:105912","journal-title":"Appl Soft Comput"},{"key":"9735_CR13","unstructured":"Fan DP, Wang W, Cheng MM, Shen J (2019) .. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8554\u20138564"},{"key":"9735_CR14","doi-asserted-by":"publisher","first-page":"1159","DOI":"10.1109\/TASLP.2020.2982297","volume":"28","author":"T Fernando","year":"2020","unstructured":"Fernando T, Sridharan S, McLaren M, Priyasad D, Denman S, Fookes C (2020) Temporarily-aware context modeling using generative adversarial networks for speech activity detection. IEEE\/ACM Transactions on Audio, Speech, and Language Processing 28:1159","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"2","key":"9735_CR15","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1121\/1.4996126","volume":"142","author":"G Firtha","year":"2017","unstructured":"Firtha G, Fiala P (2017) Wave field synthesis of moving sources with arbitrary trajectory and velocity profile. The Journal of the Acoustical Society of America 142(2):551","journal-title":"The Journal of the Acoustical Society of America"},{"key":"9735_CR16","unstructured":"Fliege J Integration nodes for the sphere. http:\/\/www.personal.soton.ac.uk\/jf1w07\/nodes\/nodes.html"},{"issue":"9","key":"9735_CR17","doi-asserted-by":"publisher","first-page":"749","DOI":"10.17743\/jaes.2017.0026","volume":"65","author":"M Frank","year":"2017","unstructured":"Frank M, Sontacchi A (2017) Case study on ambisonics for multi-venue and multi-target concerts and broadcasts. J Audio Eng Soc 65(9):749","journal-title":"J Audio Eng Soc"},{"key":"9735_CR18","unstructured":"Fu K, Fan DP, Ji GP, Zhao Q (2020) .. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 3052\u20133062"},{"key":"9735_CR19","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.neucom.2019.04.062","volume":"356","author":"K Fu","year":"2019","unstructured":"Fu K, Zhao Q, Gu IYH, Yang J (2019) Deepside: a general deep framework for salient object detection. Neurocomputing 356:69","journal-title":"Neurocomputing"},{"issue":"11","key":"9735_CR20","first-page":"859","volume":"33","author":"MA Gerzon","year":"1985","unstructured":"Gerzon MA (1985) Ambisonics in multichannel broadcasting and video. J Audio Eng Soc 33(11):859","journal-title":"J Audio Eng Soc"},{"key":"9735_CR21","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) .. In: Advances in neural information processing systems, pp 2672\u20132680"},{"issue":"6","key":"9735_CR22","doi-asserted-by":"publisher","first-page":"EL488","DOI":"10.1121\/1.5110746","volume":"145","author":"Z Han","year":"2019","unstructured":"Han Z, Wu M, Zhu Q, Yang J (2019) Three-dimensional wave-domain acoustic contrast control using a circular loudspeaker array. The Journal of the Acoustical Society of America 145(6):EL488","journal-title":"The Journal of the Acoustical Society of America"},{"key":"9735_CR23","doi-asserted-by":"crossref","unstructured":"Huygens C (1920) Trait\u00e9 de la lumi\u00e8re:... (chez Pierre vander Aa marchand libraire","DOI":"10.1259\/jrs.1920.0071"},{"issue":"6","key":"9735_CR24","doi-asserted-by":"publisher","first-page":"2542","DOI":"10.1109\/TSP.2007.893738","volume":"55","author":"RA Kennedy","year":"2007","unstructured":"Kennedy RA, Sadeghi Abhayapala TD, Jones HM (2007) Intrinsic limits of dimensionality and richness in random multipath fields. IEEE Trans Signal Process 55(6):2542","journal-title":"IEEE Trans Signal Process"},{"key":"9735_CR25","doi-asserted-by":"crossref","unstructured":"Kentgens M, Jax P (2019) .. In: ICASSP 2019-2019 IEEE international conference on acoustics, speech and signal processing (ICASSP), IEEE, pp 131\u2013135","DOI":"10.1109\/ICASSP.2019.8682250"},{"key":"9735_CR26","unstructured":"Kingma D, Ba J (2014) Adam: A method for stochastic optimization. arXiv:1412.6980"},{"issue":"5","key":"9735_CR27","doi-asserted-by":"publisher","first-page":"2992","DOI":"10.1121\/1.407330","volume":"94","author":"O Kirkeby","year":"1993","unstructured":"Kirkeby O, Nelson PA (1993) Reproduction of plane wave sound fields. The Journal of the Acoustical Society of America 94(5):2992","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"2","key":"9735_CR28","doi-asserted-by":"publisher","first-page":"811","DOI":"10.1121\/1.5023326","volume":"143","author":"P Lecomte","year":"2018","unstructured":"Lecomte P, Gauthier PA, Langrenne C, Berry A, Garcia A (2018) Cancellation of room reflections over an extended area using ambisonics. The Journal of the Acoustical Society of America 143(2):811","journal-title":"The Journal of the Acoustical Society of America"},{"key":"9735_CR29","doi-asserted-by":"publisher","first-page":"4376","DOI":"10.1109\/TIP.2019.2955241","volume":"29","author":"C Li","year":"2019","unstructured":"Li C, Guo C, Ren W, Cong R, Hou J, Kwong S, Tao D (2019) An underwater image enhancement benchmark dataset and beyond. IEEE Trans Image Process 29:4376","journal-title":"IEEE Trans Image Process"},{"key":"9735_CR30","doi-asserted-by":"crossref","unstructured":"Li C, Wand M (2016) .. In: European conference on computer vision. Springer, pp 702\u2013716","DOI":"10.1007\/978-3-319-46487-9_43"},{"key":"9735_CR31","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.inffus.2018.09.004","volume":"48","author":"J Ma","year":"2019","unstructured":"Ma J, Yu W, Liang P, Li C, Jiang J (2019) Fusiongan: a generative adversarial network for infrared and visible image fusion. Information Fusion 48:11","journal-title":"Information Fusion"},{"issue":"4","key":"9735_CR32","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1006\/jsvi.1994.1446","volume":"177","author":"PA Nelson","year":"1994","unstructured":"Nelson PA (1994) Active control of acoustic fields and the reproduction of sound. J Sound Vib 177(4):447","journal-title":"J Sound Vib"},{"key":"9735_CR33","doi-asserted-by":"crossref","unstructured":"Okamoto T (2016) .. In: 2016 IEEE international conference on acoustics, speech and signal processing (ICASSP), IEEE, pp 326\u2013330","DOI":"10.1109\/ICASSP.2016.7471690"},{"key":"9735_CR34","doi-asserted-by":"publisher","first-page":"36322","DOI":"10.1109\/ACCESS.2019.2905015","volume":"7","author":"Z Pan","year":"2019","unstructured":"Pan Z, Yu W, Yi X, Khan A, Yuan F, Zheng Y (2019) Recent progress on generative adversarial networks (gans): a survey. IEEE Access 7:36322","journal-title":"IEEE Access"},{"issue":"1","key":"9735_CR35","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1109\/TSA.2004.839244","volume":"13","author":"B Rafaely","year":"2005","unstructured":"Rafaely B (2005) Analysis and design of spherical microphone arrays. IEEE Trans Speech and Audio Process 13(1):135","journal-title":"IEEE Trans Speech and Audio Process"},{"issue":"12","key":"9735_CR36","doi-asserted-by":"publisher","first-page":"1852","DOI":"10.1109\/TASLP.2019.2934834","volume":"27","author":"N Ueno","year":"2019","unstructured":"Ueno N, Koyama S, Saruwatari H (2019) Three-dimensional sound field reproduction based on weighted mode-matching method. IEEE\/ACM Transactions on Audio, Speech, and Language Processing 27(12):1852","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"9735_CR37","doi-asserted-by":"crossref","unstructured":"Wang S, Hu R, Chen S, Wang X, Yang Y, Tu W (2015) .. In: 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP), IEEE, pp. 634\u2013638","DOI":"10.1109\/ICASSP.2015.7178046"},{"issue":"1","key":"9735_CR38","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/TPAMI.2017.2662005","volume":"40","author":"W Wang","year":"2017","unstructured":"Wang W, Shen J, Yang R, Porikli F (2017) Saliency-aware video object segmentation. IEEE Trans Pattern Anal Mach Intel 40(1):20","journal-title":"IEEE Trans Pattern Anal Mach Intel"},{"issue":"6","key":"9735_CR39","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1109\/89.943347","volume":"9","author":"DB Ward","year":"2001","unstructured":"Ward DB, Abhayapala TD (2001) Reproduction of a plane-wave sound field using an array of loudspeakers. IEEE Trans Speech and Audio process 9 (6):697","journal-title":"IEEE Trans Speech and Audio process"},{"key":"9735_CR40","doi-asserted-by":"crossref","unstructured":"Williams EG (1999) Fourier acoustics: sound radiation and nearfield acoustical holography. (Academic Press","DOI":"10.1016\/B978-012753960-7\/50007-3"},{"issue":"1","key":"9735_CR41","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1109\/TASL.2008.2005340","volume":"17","author":"YJ Wu","year":"2009","unstructured":"Wu YJ, Abhayapala TD (2009) Theory and design of soundfield reproduction using continuous loudspeaker concept. IEEE Transactions on Audio, Speech, and Language Processing 17(1):107","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9735_CR42","doi-asserted-by":"crossref","unstructured":"Xiang Y, Bao C (2020) A parallel-data-free speech enhancement method using multi- objective learning cycle-consistent generative adversarial network, IEEE\/ACM Trans- actions on Audio, Speech, and Language Processing","DOI":"10.1109\/TASLP.2020.2997118"},{"issue":"3","key":"9735_CR43","doi-asserted-by":"publisher","first-page":"EL194","DOI":"10.1121\/1.5027019","volume":"143","author":"G Yu","year":"2018","unstructured":"Yu G, Wu R, Liu Y, Xie B (2018) Near-field head-related transfer-function measurement and database of human subjects. The Journal of the Acoustical Society of America 143(3):EL194","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"7","key":"9735_CR44","doi-asserted-by":"publisher","first-page":"1184","DOI":"10.1109\/TASLP.2014.2324182","volume":"22","author":"W Zhang","year":"2014","unstructured":"Zhang W, Abhayapala TD (2014) Three dimensional sound field reproduction using multiple circular loudspeaker arrays: Functional analysis guided approach. IEEE\/ACM Transactions on Audio, Speech, and Language Processing 22(7):1184","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"9735_CR45","unstructured":"Zhang J, Fan DP, Dai Y, Anwar S, Saleh FS, Zhang T, Barnes N (2020) .. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8582\u20138591"},{"issue":"3","key":"9735_CR46","doi-asserted-by":"publisher","first-page":"1404","DOI":"10.1121\/10.0000797","volume":"147","author":"J Zhang","year":"2020","unstructured":"Zhang J, Zhang W, Abhayapala TD, Zhang L (2020) 2.5 d multizone reproduction using weighted mode matching: Performance analysis and experimental validation. The Journal of the Acoustical Society of America 147(3):1404","journal-title":"The Journal of the Acoustical Society of America"},{"key":"9735_CR47","unstructured":"Zhao JX, Liu JJ, Fan DP, Cao Y, Yang J, Cheng MM (2019) .. In: Proceedings of the IEEE International Conference on Computer Vision, pp 8779\u20138788"},{"key":"9735_CR48","unstructured":"Zhu JY, Park T, Isola P, Efros AA (2017) .. In: Proceedings of the IEEE international conference on computer vision, pp 2223\u20132232"},{"issue":"1","key":"9735_CR49","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1121\/10.0000474","volume":"147","author":"Q Zhu","year":"2020","unstructured":"Zhu Q, Qiu X, Coleman P, Burnett I (2020) A comparison between two modal domain methods for personal audio reproduction. The Journal of the Acoustical Society of America 147(1):161","journal-title":"The Journal of the Acoustical Society of America"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-09735-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-020-09735-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-09735-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,11]],"date-time":"2021-09-11T23:26:20Z","timestamp":1631402780000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-020-09735-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,12]]},"references-count":49,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["9735"],"URL":"https:\/\/doi.org\/10.1007\/s11042-020-09735-3","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2020,9,12]]},"assertion":[{"value":"17 January 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 August 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 September 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}