{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:13:39Z","timestamp":1740132819741,"version":"3.37.3"},"reference-count":21,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Institute of Information and Communications Technology Planning and Evaluation","award":["2021-0-00456"],"award-info":[{"award-number":["2021-0-00456"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/lsp.2021.3132557","type":"journal-article","created":{"date-parts":[[2021,12,3]],"date-time":"2021-12-03T20:25:04Z","timestamp":1638563104000},"page":"244-248","source":"Crossref","is-referenced-by-count":2,"title":["Neurally Optimized Decoder for Low Bitrate Speech Codec"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6009-9530","authenticated-orcid":false,"given":"Hyung Yong","family":"Kim","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8631-4489","authenticated-orcid":false,"given":"Ji Won","family":"Yoon","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8882-9125","authenticated-orcid":false,"given":"Won Ik","family":"Cho","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0568-4902","authenticated-orcid":false,"given":"Nam Soo","family":"Kim","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"WaveNet: A generative model for raw audio,","year":"2016","author":"van den Oord","key":"ref1"},{"key":"ref2","first-page":"2410","article-title":"Efficient neural audio synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kalchbrenner","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053657"},{"key":"ref5","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"van den Oord","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.540325"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1255"},{"article-title":"Codec 2-open source speech coding at 2400 bit\/s and below","year":"2011","author":"Rowe","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.804299"},{"key":"ref11","first-page":"232","article-title":"IMBE and AMBE speech compression","volume-title":"Proc. Int. IC","author":"Rudolph","year":"1999"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1255"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49127-9"},{"key":"ref14","first-page":"6199","article-title":"Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech Signal Process","author":"Song","year":"2020"},{"article-title":"Conditional generative adversarial nets","year":"2014","author":"Mirza","key":"ref15"},{"key":"ref16","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Proc. Adv. Neural Inf. Process. Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.6028\/nist.ir.4930"},{"volume-title":"Test signals for use in telephony and other speech-based applications, Rec. ITU-T P.501","year":"2012","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"journal-title":"Method for the subjective assessment of intermediate quality levels of coding systems, Rec. ITU-T BS.1534-3","year":"2015","key":"ref20"},{"volume-title":"Methods for subjective determination of transmission quality, Rec. ITU-T P.800","year":"1996","key":"ref21"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/9686799\/09635650.pdf?arnumber=9635650","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T20:13:41Z","timestamp":1709324021000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9635650\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/lsp.2021.3132557","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2022]]}}}