{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T14:26:12Z","timestamp":1740147972986,"version":"3.37.3"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/jstsp.2024.3482721","type":"journal-article","created":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T17:36:46Z","timestamp":1729186606000},"page":"1506-1516","source":"Crossref","is-referenced-by-count":0,"title":["MDCTNet: A Hybrid Approach to Neural Audio Coding"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3011-5476","authenticated-orcid":false,"given":"Lars","family":"Villemoes","sequence":"first","affiliation":[{"name":"Advanced Technology Group, Dolby Sweden AB, Stockholm, SE, Sweden"}]},{"given":"Mark","family":"Vinton","sequence":"additional","affiliation":[{"name":"Advanced Technology Group, Dolby Laboratories, Inc., San Francisco, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8893-2668","authenticated-orcid":false,"given":"Per","family":"Ekstrand","sequence":"additional","affiliation":[{"name":"Advanced Technology Group, Dolby Sweden AB, Stockholm, SE, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1856-8556","authenticated-orcid":false,"given":"Lie","family":"Lu","sequence":"additional","affiliation":[{"name":"Advanced Technology Group, Dolby Laboratories, Inc., San Francisco, CA, USA"}]},{"given":"Grant","family":"Davidson","sequence":"additional","affiliation":[{"name":"Advanced Technology Group, Dolby Laboratories, Inc., San Francisco, CA, USA"}]},{"given":"Cong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Advanced Technology Group, Dolby Laboratories, Inc., San Francisco, CA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682435"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1255"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415120"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129353"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447532"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2263371"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref9","first-page":"1","article-title":"High fidelity neural audio compression","author":"Dfossez","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref10","first-page":"27980","article-title":"High-fidelity audio compression with improved RVQGAN","volume":"36","author":"Kumar","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164954"},{"key":"ref12","first-page":"1","article-title":"Music enhancement by a novel CNN architecture","volume-title":"Proc. Audio Eng. Soc. Conv. 145 Audio Eng. Soc.","author":"Porov"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053113"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04158-0"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10111349"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747733"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1204"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448332"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682268"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054409"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3172853"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096056"},{"issue":"8","key":"ref24","first-page":"1","article-title":"An efficient implementation of the Patterson-Holdsworth filter bank","volume":"35","author":"Slaney","year":"1993","journal-title":"Apple Comput. Percep. Group, Tech. Rep."},{"key":"ref25","first-page":"1","article-title":"A new perceptual model for audio coding based on spectro-temporal masking","volume-title":"Proc. Audio Eng. Soc. Conv. 124, Audio Eng. Soc.","author":"Kohlrausch"},{"key":"ref26","first-page":"1","article-title":"A nonlinear psychoacoustic model applied to ISOMPEG layer 3 coder","volume-title":"Proc. Audio Eng. Soc. Conv. 99, Audio Eng. Soc.","author":"Baumgarte"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/5.842996"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053220"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170048"},{"article-title":"Melnet: A generative model for audio in the frequency domain","year":"2019","author":"Vasquez","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3271145"},{"article-title":"Improving neural networks by preventing co-adaptation of feature detectors","year":"2012","author":"Hinton","key":"ref32"},{"key":"ref33","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"year":"2022","key":"ref35","article-title":"ViSQOL"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX48832.2020.9123105"},{"key":"ref37","first-page":"1","article-title":"Generative machine listener","volume":"155","author":"Guanxin","year":"2023","journal-title":"Audio Eng. Soc. Conv."},{"article-title":"Definition of the Opus audio codec","year":"2012","author":"Valin","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2013.24"},{"year":"2015","key":"ref40","article-title":"Method for the subjective assessment of intermediate quality levels of coding systems"},{"year":"2011","key":"ref41","article-title":"USAC verification test report"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/10874827\/10720937.pdf?arnumber=10720937","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T18:37:34Z","timestamp":1738867054000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10720937\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":40,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2024.3482721","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"type":"print","value":"1932-4553"},{"type":"electronic","value":"1941-0484"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}