{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T01:44:53Z","timestamp":1770342293003,"version":"3.49.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Electronics and Telecommunications Research Institute funded by the Korean Government","award":["24ZC1100"],"award-info":[{"award-number":["24ZC1100"]}]},{"name":"Research of the Basic Media-Contents Technologies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/jstsp.2024.3501681","type":"journal-article","created":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T18:55:28Z","timestamp":1731956128000},"page":"1414-1426","source":"Crossref","is-referenced-by-count":3,"title":["Improved Alias-and-Separate Speech Coding Framework With Minimal Algorithmic Delay"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5576-7792","authenticated-orcid":false,"given":"Eunkyun","family":"Lee","sequence":"first","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6254-2062","authenticated-orcid":false,"given":"Seungkwon","family":"Beack","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute, Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8910-0264","authenticated-orcid":false,"given":"Jong Won","family":"Shin","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, Gwangju, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSPA.2005.1581010"},{"key":"ref2","article-title":"The effect of bandwidth on speech intelligibility","author":"Rodman","year":"2006"},{"key":"ref3","volume-title":"Mandatory Speech Codec Speech Processing Functions, Adaptive Multi-Rate (AMR) Speech Codec, Transcoding Functions","year":"1999"},{"key":"ref4","volume-title":"Enhanced Variable Rate Codec, Speech Service Option 3 for Wideband Spread Spectrum Digital Systems","year":"2004"},{"key":"ref5","volume-title":"Wideband Coding of Speech at Around 16 Kbit\/s Using Adaptive Multi-Rate Wideband (AMR-WB)","year":"2003"},{"key":"ref6","volume-title":"Enhanced Variable Rate Codec, Speech Service Options 3, 68, and 70 for Wideband Spread Spectrum Digital Systems","year":"2007"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.17487\/rfc6716"},{"key":"ref8","volume-title":"Codec for Enhanced Voice Services (EVS), Ansi C Code (Floating-Point)","year":"2022"},{"key":"ref9","first-page":"3406","article-title":"A real-time wideband neural vocoder at 1.6 kb\/s using LPCNet","volume-title":"Proc. Annu. Conf. Int. Speech Commun. Assoc.","author":"Valin","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref11","article-title":"High fidelity neural audio compression","author":"Dfossez","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445966"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447744"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178801"},{"key":"ref16","first-page":"1","article-title":"Audio super-resolution using neural nets","volume-title":"Proc. Int. Conf. Learn. Representations (Workshop Track)","author":"Kuleshov","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3054302"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2909077"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413439"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3190726"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096301"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095382"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3349053"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-36"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-45"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3207381"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref28","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Kumar","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref30","first-page":"3291","article-title":"Real time speech enhancement in the waveform domain","volume-title":"Proc. Annu. Conf. Int. Speech Commun. Assoc.","author":"Dfossez","year":"2020"},{"key":"ref31","volume-title":"Discrete-Time Signal Processing","author":"Oppenheim","year":"2009"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3122"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2021.103109"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP49062.2020.9231900"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096956"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3078640"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052981"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3101617"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053113"},{"key":"ref43","article-title":"TIMIT acoustic-phonetic continuous speech corpus LDC93S1","volume-title":"Proc. Philadelphia, Linguistic Data Consortium","author":"Garofolo","year":"1993"},{"key":"ref44","article-title":"CSR-I (WSJ0) complete LDC93S6A","volume-title":"Proc. Philadelphia, Linguistic Data Consortium","author":"Garofolo","year":"1993"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-159"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3108784"},{"key":"ref47","article-title":"WaveNet: A generative model for raw audio","author":"Oord","year":"2016"},{"key":"ref48","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref49","volume-title":"Wideband Extension to Recommendation P.862 for the Assessment of Wideband Telephone Networks and Speech Codecs","year":"2007"},{"key":"ref50","volume-title":"Perceptual Evaluation of Speech Quality (PESQ): An Objective Method for End-to-End Speech Quality Assessment of Narrow-Band Telephone Networks and Speech Codecs","year":"2001"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref52","volume-title":"Method for the Subjective Assessment of Intermediate Quality Level of Audio Systems","year":"2015"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/10874827\/10756718.pdf?arnumber=10756718","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T06:04:10Z","timestamp":1738821850000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10756718\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":52,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2024.3501681","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}