{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:13:23Z","timestamp":1776885203287,"version":"3.51.2"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053220","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"341-345","source":"Crossref","is-referenced-by-count":10,"title":["Source Coding of Audio Signals with a Generative Model"],"prefix":"10.1109","author":[{"given":"Roy","family":"Fejgin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Janusz","family":"Klejsa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lars","family":"Villemoes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cong","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Music enhancement by a novel CNN architecture","volume":"145","author":"porov","year":"2018","journal-title":"Audio Engineering Society Convention"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682268"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04158-0"},{"key":"ref13","first-page":"401","article-title":"Quantization with constrained relative entropy and its application to audio coding","author":"li","year":"2009","journal-title":"Audio Engineering Society Convention 127 2009"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2010.2087749"},{"key":"ref15","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"den oord","year":"2017"},{"key":"ref16","article-title":"ADAM: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref17","article-title":"Method for the subjective assessment of intermediate quality levels of coding systems","year":"2015","journal-title":"Recommendation ITU-R BS 1534-2"},{"key":"ref18","article-title":"Definition of the Opus audio codec","author":"valin","year":"2012","journal-title":"IETF RFC 6716"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.918684"},{"key":"ref4","article-title":"Improving Opus low bit rate quality with neural speech synthesis","author":"skoglund","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1255"},{"key":"ref6","article-title":"Wavenet: A generative model for raw audio","author":"den oord","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref8","article-title":"Gansynth: Adversarial neural audio synthesis","author":"engel","year":"2019"},{"key":"ref7","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","author":"mehri","year":"2016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682435"},{"key":"ref9","article-title":"Enabling factorized piano music modeling and generation with the MAESTRO dataset","author":"hawthorne","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2013.24"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.804299"},{"key":"ref21","article-title":"CSR-I (WSJ0) complete LDC93S6A","author":"garofolo","year":"1993"},{"key":"ref24","article-title":"Rethinking lossy compression: The rate-distortion-perception tradeoff","author":"blau","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00652"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053220.pdf?arnumber=9053220","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:26:10Z","timestamp":1656361570000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053220\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053220","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}