{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T16:49:59Z","timestamp":1792687799210,"version":"4.5.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413678","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"706-710","source":"Crossref","is-referenced-by-count":17,"title":["Source-Aware Neural Speech Coding for Noisy Speech Compression"],"prefix":"10.1109","author":[{"given":"Haici","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Zhen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seungkwon","family":"Beack","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minje","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1985.1168147"},{"key":"ref11","article-title":"Information technology - mpeg audio technologies - part 3: Unified speech and audio coding","year":"2011"},{"key":"ref12","article-title":"Transport of unified speech and audio coding (USAC)","year":"2011"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179102"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2014.0049"},{"key":"ref15","article-title":"Intelligent gap filling in perceptual transform coding of audio","author":"disch","year":"2016","journal-title":"Audio Engineering Society Convention 141"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053657"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref19","article-title":"TIMIT acoustic- phonetic continuous speech corpus","author":"garofolo","year":"1993"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref3","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461487"},{"key":"ref5","article-title":"A real-time wideband neural vocoder at 1.6 kb\/s using LPCNet","author":"valin","year":"2019","journal-title":"Proceedings of the Annual Conference of the International Speech Communication Association (Interspeech)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054347"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1816"},{"key":"ref2","first-page":"1141","article-title":"Soft-to-hard vector quantization for end-to-end learning compressible representations","author":"agustsson","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.804299"},{"key":"ref1","article-title":"Lossy image compression with compressive autoencoders","author":"theis","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-28551-6_5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref24","article-title":"Definition of the opus audio codec","author":"valin","year":"2012"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref25","article-title":"SDR - half-baked or well done?","author":"le roux","year":"2018"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413678.pdf?arnumber=9413678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:04Z","timestamp":1652197264000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413678\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413678","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}