{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:06:42Z","timestamp":1766066802073,"version":"3.37.3"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2018,8,1]],"date-time":"2018-08-01T00:00:00Z","timestamp":1533081600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/3.0\/legalcode"}],"funder":[{"name":"EPSRC Programme Grant S3A: Future Spatial Audio for an Immersive Listener Experience at Home","award":["EP\/L000539\/1"],"award-info":[{"award-number":["EP\/L000539\/1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1109\/tmm.2018.2794780","type":"journal-article","created":{"date-parts":[[2018,1,17]],"date-time":"2018-01-17T19:21:16Z","timestamp":1516216876000},"page":"1919-1931","source":"Crossref","is-referenced-by-count":30,"title":["An Audio-Visual System for Object-Based Audio: From Recording to Listening"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3266-7358","authenticated-orcid":false,"given":"Philip","family":"Coleman","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4707-6710","authenticated-orcid":false,"given":"Andreas","family":"Franck","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3227-5001","authenticated-orcid":false,"given":"Jon","family":"Francombe","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0778-2992","authenticated-orcid":false,"given":"Qingju","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Teofilo","family":"de Campos","sequence":"additional","affiliation":[]},{"given":"Richard J.","family":"Hughes","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1475-8798","authenticated-orcid":false,"given":"Dylan","family":"Menzies","sequence":"additional","affiliation":[]},{"given":"Marcos F. Simon","family":"Galvez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1149-4272","authenticated-orcid":false,"given":"Yan","family":"Tang","sequence":"additional","affiliation":[]},{"given":"James","family":"Woodcock","sequence":"additional","affiliation":[]},{"given":"Philip J. B.","family":"Jackson","sequence":"additional","affiliation":[]},{"given":"Frank","family":"Melchior","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6638-7645","authenticated-orcid":false,"given":"Chris","family":"Pike","sequence":"additional","affiliation":[]},{"given":"Filippo Maria","family":"Fazi","sequence":"additional","affiliation":[]},{"given":"Trevor J.","family":"Cox","sequence":"additional","affiliation":[]},{"given":"Adrian","family":"Hilton","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008935410038"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37762-4_2"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.05.006"},{"key":"ref70","first-page":"1","article-title":"A\n reference listening room for 3D audio research","author":"nixon","year":"2015","journal-title":"Proc Int Conf Spatial Audio"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref74","article-title":"Production and reproduction of program\n material for a variety of spatial audio formats","author":"francombe","year":"2015","journal-title":"Proc Audio Eng Soc Conv 138"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362551"},{"journal-title":"International Telecommunication Union Geneva Switzerland","article-title":"Recommendation ITU-R BS.1116-3, Methods for the subjective assessment of small\n impairments in audio systems","year":"2015","key":"ref75"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2016.0071"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/0165-1684(94)90029-9"},{"article-title":"Object-based audio capture: Separating acoustically-mixed sounds","year":"1999","author":"westner","key":"ref32"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162830"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471928"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2580946"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2031510"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2029711"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-22794-6_12"},{"key":"ref60","article-title":"Descriptive\n analysis of binaural rendering with virtual loudspeakers using a rate-all-that-apply approach","author":"pike","year":"2016","journal-title":"Proc Int Conf Headphone Technol"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1121\/1.423763"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/6046.845012"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1121\/1.1513363"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2459017"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2162581"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2301977"},{"key":"ref65","first-page":"1","article-title":"Sweet-spot-independent binaural reproduction with a\n listener-adaptive loudspeaker array","author":"g\u00e1lvez","year":"2016","journal-title":"Proc 22nd Int Congr Acoust"},{"key":"ref66","article-title":"A listener adaptive optimal source distribution system for virtual sound imaging","author":"g\u00e1lvez","year":"2016","journal-title":"Proc 140 Conv Audio Eng Soc"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2003.1261119"},{"key":"ref67","article-title":"Presenting the S3A object-based audio drama\n dataset","author":"woodcock","year":"2016","journal-title":"Proc 140 Conv Audio Eng Soc"},{"journal-title":"International Telecommunication Union Geneva Switzerland","article-title":"Recommendation ITU-R BS.2051-0: Advanced sound system for programme reproduction","year":"2014","key":"ref68"},{"key":"ref69","first-page":"29","article-title":"A spherical far field HRIR\/HRTF compilation of the Neumann KU 100","author":"bernsch\u00fctz","year":"0","journal-title":"Proc 40th Italian Annu Conf Acoust \/39th German Annu Conf Acoust"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2264784"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/9781118706350.ch2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2013.6618221"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2442151"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-013-1472-2"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.63"},{"key":"ref23","first-page":"149","article-title":"A survey on human motion analysis from depth data","volume":"8200","author":"ye","year":"2013","journal-title":"Time-of-Flight and Depth Imaging Sensors Algorithms and Applications"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459377"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0549-0"},{"key":"ref50","article-title":"An assessment of virtual surround sound systems for headphone listening of 5.1 multichannel\n audio","author":"pike","year":"2013","journal-title":"Proc Audio Eng Soc Conv 134"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1017\/S1355771810000324"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2016.0027"},{"key":"ref58","article-title":"A listener position adaptive stereo\n system for object-based reproduction","author":"g\u00e1lvez","year":"2015","journal-title":"Proc Audio Eng Soc Conv 138"},{"key":"ref57","first-page":"456","article-title":"Virtual sound source positioning using vector base amplitude\n panning","volume":"45","author":"pulkki","year":"1997","journal-title":"J Audio Eng Soc"},{"key":"ref56","first-page":"807","article-title":"All-round ambisonic panning and decoding","volume":"60","author":"zotter","year":"2012","journal-title":"J Audio Eng Soc"},{"key":"ref55","first-page":"183","article-title":"An\n open-source C++ framework for multithreaded realtime multichannel audio applications","author":"geier","year":"2012","journal-title":"Proc Linux Conf Au"},{"key":"ref54","article-title":"Design, coding and processing of metadata for\n object-based interactive audio","author":"f\u00fcg","year":"2014","journal-title":"Proc Audio Eng Soc Conv 137"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2016.0059"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1162\/COMJ_a_00167"},{"journal-title":"MDA Object-Based Audio Immersive Sound Metadata and Bitstream","year":"2015","key":"ref10"},{"journal-title":"Digital audio compression (AC-4) standard part 2 Immersive and personalized audio","year":"2015","key":"ref11"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/53.665"},{"journal-title":"AC-4 Object Audio Renderer for Consumer Use","year":"2016","key":"ref12"},{"article-title":"D2.2: Interim reference architecture\n specification and integration report","year":"2017","author":"weitnauer","key":"ref13"},{"journal-title":"Spatial Audio","year":"2001","author":"rumsey","key":"ref14"},{"journal-title":"Sound and Recording An Introduction","year":"2006","author":"rumsey","key":"ref15"},{"journal-title":"Component-Based Software Engineering Putting the Pieces Together","year":"2001","author":"heineman","key":"ref16"},{"journal-title":"Internet Engineering Task Force RFC","article-title":"RFC 7159—The JavaScript Object Notation (JSON) data interchange format","year":"2014","key":"ref17"},{"key":"ref18","article-title":"An open 3D audio production chain proposed by\n the Edison 3D project","author":"corteel","year":"2016","journal-title":"Proc 140 Conv Audio Eng Soc"},{"key":"ref19","article-title":"Object-based 3D audio production for\n virtual reality using the audio definition model","author":"pike","year":"2016","journal-title":"Proc AES Int Conf Audio Virtual Augmented Reality"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2512142.2512152"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2015.0017"},{"key":"ref6","first-page":"12","article-title":"Object-based broadcasting—Curation,\n responsiveness and user experience","author":"armstrong","year":"2014","journal-title":"Proc IBC Conf"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1049\/ibc.2016.0034"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2015.2411578"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1002\/9781118706350.ch4"},{"journal-title":"International Telecommunication Union Geneva Switzerland","article-title":"Recommendation BS.1770-4: Algorithms to measure audio programme loudness and\n true-peak audio level","year":"2015","key":"ref49"},{"year":"2015","key":"ref9","article-title":"Recommendation BS.2076-0: Audio Definition Model"},{"key":"ref46","first-page":"2568","article-title":"A glimpse-based approach for\n predicting binaural intelligibility with single and multiple maskers in anechoic conditions","author":"tang","year":"2015","journal-title":"Proc INTERSPEECH"},{"journal-title":"AES Recommended Practice for Digital Audio Engineering—Serial Multichannel Audio Digital Interface (MADI)","year":"1991","key":"ref45"},{"key":"ref48","article-title":"Loudness matching multichannel audio\n programme material with listeners and predictive models","author":"francombe","year":"2015","journal-title":"Proc Audio Eng Soc Conv 139"},{"key":"ref47","article-title":"Subjective loudness of 22.2 multichannel\n programs","author":"komori","year":"2015","journal-title":"Proc Audio Eng Soc Conv 138"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205285"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2010.938754"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-016-0306-6"},{"key":"ref43","article-title":"Audio object separation using microphone array beamforming","author":"coleman","year":"2015","journal-title":"Proc Audio Eng Soc Conv 138"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8411794\/08260969.pdf?arnumber=8260969","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T12:30:34Z","timestamp":1643200234000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8260969\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8]]},"references-count":78,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2018.2794780","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2018,8]]}}}