{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T18:26:50Z","timestamp":1770748010792,"version":"3.49.0"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Korea government","doi-asserted-by":"publisher","award":["2017-0-00072"],"award-info":[{"award-number":["2017-0-00072"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/lsp.2020.3039765","type":"journal-article","created":{"date-parts":[[2020,11,20]],"date-time":"2020-11-20T20:24:52Z","timestamp":1605903892000},"page":"2159-2163","source":"Crossref","is-referenced-by-count":28,"title":["Psychoacoustic Calibration of Loss Functions for Efficient End-to-End Neural Audio Coding"],"prefix":"10.1109","volume":"27","author":[{"given":"Kai","family":"Zhen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mi Suk","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jongmo","family":"Sung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seungkwon","family":"Beack","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3513-8328","authenticated-orcid":false,"given":"Minje","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Method for the subjective assessment of intermediate quality levels of coding systems (MUSHRA)","year":"2003"},{"key":"ref32","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054347"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682315"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081412"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937189"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-88"},{"key":"ref15","article-title":"On psychoacoustically weighted cost functions towards resource-efficient deep neural networks for speech denoising","author":"zhen","year":"0","journal-title":"arXiv 1801 09774"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2821903"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2871419"},{"key":"ref28","author":"salomon","year":"2004","journal-title":"Data Compression The Complete Reference"},{"key":"ref4","first-page":"1068","article-title":"Neural audio synthesis of musical notes with waveNet autoencoders","author":"engel","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.1983.1091516"},{"key":"ref3","first-page":"780","article-title":"ISO\/MPEG-1 audio: A generic standard for coding of high-quality digital audio","volume":"42","author":"brandenburg","year":"1994","journal-title":"J Audio Eng Soc"},{"key":"ref6","first-page":"7155","article-title":"High-quality speech coding with SampleRNN","author":"klejsa","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"571","DOI":"10.1109\/TCE.2005.1468003","article-title":"A low-complexity MP3 algorithm that uses a new rate control and a fast dequantization","volume":"51","author":"yen","year":"2005","journal-title":"IEEE Trans Consum Electron"},{"key":"ref5","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"arXiv 1609 03499"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref7","first-page":"334","article-title":"Wave-U-Net: A multi-scale neural network for end-to-end audio source separation","author":"stoller","year":"0","journal-title":"Proc Int Conf Music Inf Retrieval"},{"key":"ref2","article-title":"Coding of moving pictures and associated audio for digital storage media at up to about 1.5 mbit\/s","year":"1993"},{"key":"ref9","first-page":"6306","article-title":"Neural discrete representation learning","author":"van den oord","year":"0","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref1","first-page":"789","article-title":"ISO\/IEC MPEG-2 advanced audio coding","volume":"45","author":"bosi","year":"1997","journal-title":"J Audio Eng Soc"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/5.842996"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2876171"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461487"},{"key":"ref24","first-page":"1141","article-title":"Soft-to-hard vector quantization for end-to-end learning compressible representations","author":"agustsson","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1816"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/8966529\/09265269.pdf?arnumber=9265269","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:46:57Z","timestamp":1651070817000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9265269\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/lsp.2020.3039765","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}