{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T15:17:04Z","timestamp":1725808624034},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10445853","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1131-1135","source":"Crossref","is-referenced-by-count":0,"title":["SPATIALCODEC: Neural Spatial Speech Coding"],"prefix":"10.1109","author":[{"given":"Zhongweiyang","family":"Xu","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana-Champaign"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Xu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vinay","family":"Kothapally","sequence":"additional","affiliation":[{"name":"Tencent AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heming","family":"Wang","sequence":"additional","affiliation":[{"name":"The Ohio State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muqiao","family":"Yang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168147"},{"article-title":"Speex: A free codec for free speech","year":"2016","author":"Valin","key":"ref2"},{"article-title":"High-quality, low-delay music coding in the opus codec","year":"2016","author":"Valin","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179063"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2006.1706505"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-05660-9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3626-0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3129994"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3277693"},{"article-title":"High fidelity neural audio compression","year":"2022","author":"D\u00e9fossez","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"article-title":"HiFi-Codec: Group-residual vector quantization for high fidelity audio codec","year":"2023","author":"Yang","key":"ref12"},{"article-title":"Neural discrete representation learning","year":"2017","author":"Van den Oord","key":"ref13"},{"article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","year":"2019","author":"Kumar","key":"ref14"},{"article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","year":"2020","author":"Kong","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"article-title":"Simple and controllable music generation","year":"2023","author":"Copet","key":"ref17"},{"article-title":"Neural codec language models are zero-shot text to speech synthesizers","year":"2023","author":"Wang","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1155\/9789775945242"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1155\/ASP.2005.1305"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2015.2411578"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.930433"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICSP48669.2020.9321083"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2955818"},{"article-title":"AISHELL-2: Transforming mandarin asr research into industrial scale","year":"2018","author":"Du","key":"ref25"},{"article-title":"DNS-MOS p.835: A non-intrusive perceptual objective speech quality metric to evaluate noise suppressors","year":"2022","author":"Reddy","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93764-9_23"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.1986.1143830"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461310"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/sym14061081"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101976"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10445853.pdf?arnumber=10445853","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:56:56Z","timestamp":1722574616000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445853\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10445853","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}