{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T04:44:31Z","timestamp":1775623471382,"version":"3.50.1"},"reference-count":97,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61936015"],"award-info":[{"award-number":["61936015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["6240071246"],"award-info":[{"award-number":["6240071246"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["24ZR1430600"],"award-info":[{"award-number":["24ZR1430600"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Key Laboratory of Trusted Data Circulation and Governance"},{"name":"Web3"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tmc.2025.3634628","type":"journal-article","created":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T18:48:06Z","timestamp":1763578086000},"page":"5969-5987","source":"Crossref","is-referenced-by-count":0,"title":["Aucom: Extreme Compression for Real-Time Edge-to-Server Universal Audio Streaming"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9024-3692","authenticated-orcid":false,"given":"Yu","family":"Lu","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ran","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2190-0919","authenticated-orcid":false,"given":"Dian","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7129-6764","authenticated-orcid":false,"given":"Yijie","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computing, National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longyuan","family":"Ge","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9170-8479","authenticated-orcid":false,"given":"Juntao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2716-5369","authenticated-orcid":false,"given":"Yongzhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0782-4953","authenticated-orcid":false,"given":"Yi-Chao","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2725-2529","authenticated-orcid":false,"given":"Jiannong","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Computing, Hong Kong Polytechnic University, Hung Hom, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1617-3593","authenticated-orcid":false,"given":"Guangtao","family":"Xue","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/9781003564966-97"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.17487\/rfc9639"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.11591\/ijece.v8i1.pp70-75"},{"key":"ref4","first-page":"1","article-title":"APE: Audio perceptual evaluation toolbox for MATLAB","volume-title":"Proc. 136th Conv. Audio Eng. Soc.","author":"De Man"},{"key":"ref5","first-page":"1","volume-title":"WAV Format Preservation Assessment","author":"Whibley","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1515\/9780822395522"},{"key":"ref7","first-page":"1","article-title":"MP3 and AAC explained","volume-title":"Proc. 17th Int. Conf.: High-Qual. Audio Coding Audio Eng. Soc. Conf.","author":"Brandenburg"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1214"},{"key":"ref9","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3447993.3448628"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3416300"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1202279"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947651"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref18","article-title":"Rethinking CNN models for audio classification","author":"Palanisamy","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096787"},{"key":"ref20","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.challengehml-1.1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120633"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3247"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-1446"},{"key":"ref25","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096513"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref30","article-title":"The LJ speech dataset","author":"Ito","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.65286\/icic.v20i2.69839"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00563"},{"key":"ref35","article-title":"Deep contextual video compression","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref36","article-title":"VCT: A video compression transformer","author":"Mentzer","year":"2022"},{"key":"ref37","article-title":"Density modeling of images using a generalized normalization transformation","author":"Ball\u00e9","year":"2015"},{"key":"ref38","first-page":"1","article-title":"Lossy image compression with compressive autoencoders","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Theis"},{"key":"ref39","first-page":"2922","article-title":"Real-time adaptive image compression","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rippel"},{"key":"ref40","article-title":"Asymmetric numeral systems","author":"Duda","year":"2009"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/31846.42227"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1973.9200"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3631460"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3631447"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683634"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2207"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746169"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2828980"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683016"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053591"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747578"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096646"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445985"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.12.003"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-517"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3116502"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6489"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1441"},{"key":"ref64","article-title":"Rethinking attention with performers","author":"Choromanski","year":"2020"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref66","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"Ulyanov","year":"2016"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72949-2_21"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-599"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096553"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/79.952802"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1981.1056282"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref76","article-title":"End-to-end optimized image compression","author":"Ball\u00e9","year":"2016"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.577"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-24"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref80","first-page":"1015","article-title":"ESC: Dataset for environmental sound classification","volume-title":"Proc. 23rd ACM Int. Conf. Multimedia","author":"Piczak"},{"key":"ref81","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018"},{"key":"ref82","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref83","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref84","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57077-4_10"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3650212.3680374"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-3156-2_2"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3430898"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428249"},{"key":"ref90","first-page":"2031","article-title":"MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fu"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746171"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-565"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746273"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1147\/rd.232.0149"},{"key":"ref95","first-page":"486","article-title":"Adaptive range coding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Rosen"},{"key":"ref97","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020"},{"key":"ref98","first-page":"9361","article-title":"SqueezeFormer: An efficient transformer for automatic speech recognition","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kim"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11471282\/11259080.pdf?arnumber=11259080","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T03:46:39Z","timestamp":1775619999000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11259080\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":97,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2025.3634628","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}