{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T14:54:50Z","timestamp":1781016890087,"version":"3.54.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746978","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"426-430","source":"Crossref","is-referenced-by-count":4,"title":["Upmixing Via Style Transfer: A Variational Autoencoder for Disentangling Spatial Images And Musical Content"],"prefix":"10.1109","author":[{"given":"Haici","family":"Yang","sequence":"first","affiliation":[{"name":"Indiana University,Dept. of Intelligent Systems Engineering,Bloomington,IN,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanna","family":"Wager","sequence":"additional","affiliation":[{"name":"Amazon Lab126,Cambridge,MA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Spencer","family":"Russell","sequence":"additional","affiliation":[{"name":"Amazon Lab126,Cambridge,MA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mike","family":"Luo","sequence":"additional","affiliation":[{"name":"Amazon Lab126,Cambridge,MA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minje","family":"Kim","sequence":"additional","affiliation":[{"name":"Indiana University,Dept. of Intelligent Systems Engineering,Bloomington,IN,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wontak","family":"Kim","sequence":"additional","affiliation":[{"name":"Amazon Lab126,Cambridge,MA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5909\/JBE.2012.17.6.924"},{"key":"ref11","first-page":"227","article-title":"Primary-ambient extraction in audio signals using adaptive weighting and principal component analysis","author":"ibrahim","year":"2016","journal-title":"Proc Sound and Music Computing Conference (SMC)"},{"key":"ref12","article-title":"A supervised learning approach to ambience extraction from mono recordings for blind upmixing","author":"uhle","year":"2008","journal-title":"Proc Int Conf Digital Audio Effects (DAFx)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461459"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2020.0020"},{"key":"ref15","article-title":"Stereo signal separation and upmixing by mid-side decomposition in the frequency-domain","author":"kraft","year":"2015","journal-title":"International Conference on Digital Audio Effects (DAFx)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC.2016.7763500"},{"key":"ref17","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref19","first-page":"456","article-title":"Virtual sound source positioning using vector base amplitude panning","volume":"45","author":"pulkki","year":"1997","journal-title":"Journal of the Audio Engineering Society"},{"key":"ref4","article-title":"Robust representation of spatial sound in stereo-to-multichannel up-mix","author":"jeon","year":"2010","journal-title":"Audio Engineering Society Convention 128"},{"key":"ref3","first-page":"1051","article-title":"Multiple-loudspeaker playback of stereo signals","volume":"54","author":"faller","year":"2006","journal-title":"Journal of the Audio Engineering Society"},{"key":"ref6","article-title":"Frequency domain techniques for stereo to multichannel upmix","author":"avendano","year":"2002","journal-title":"Journal of the Audio Engineering Society"},{"key":"ref5","first-page":"ii-1957?ii","article-title":"Ambience extraction and synthesis from stereo signals for multi-channel audio up-mix","volume":"2","author":"avendano","year":"2002","journal-title":"2002 IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref8","first-page":"914","article-title":"Two-to-five channel sound processing","volume":"50","author":"irwan","year":"2002","journal-title":"Journal of the Audio Engineering Society"},{"key":"ref7","article-title":"Correlation-based ambience extraction from stereo recordings","author":"merimaa","year":"2007","journal-title":"Journal of the Audio Engineering Society"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2011.6082279"},{"key":"ref1","article-title":"Optimal reproduction matrices for multi-speaker stereo","author":"gerzon","year":"1991","journal-title":"Audio Eng Soc Convention"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.901832"},{"key":"ref20","article-title":"Multichannel stereophonic sound system with and without accompanying picture","year":"2012"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"ref21","article-title":"MUSDB18-HQ - an uncompressed version of MUSDB18","author":"rafii","year":"2019"},{"key":"ref24","article-title":"Wave-u-net: A multi-scale neural network for end-to-end audio source separation","author":"stoller","year":"2018","journal-title":"Proceedings of the International Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref23","article-title":"SDR – half-baked or well done?","author":"le roux","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746978.pdf?arnumber=9746978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T16:13:03Z","timestamp":1661184783000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746978\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746978","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}