{"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":1740132819030,"version":"3.37.3"},"reference-count":24,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/L000539\/1"],"award-info":[{"award-number":["EP\/L000539\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BBC Audio Research Partnership"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/lsp.2019.2951894","type":"journal-article","created":{"date-parts":[[2019,11,6]],"date-time":"2019-11-06T20:49:27Z","timestamp":1573073367000},"page":"1872-1876","source":"Crossref","is-referenced-by-count":5,"title":["A Speech Synthesis Approach for High Quality Speech Separation and Generation"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0778-2992","authenticated-orcid":false,"given":"Qingju","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip J.B.","family":"Jackson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8393-5703","authenticated-orcid":false,"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462431"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref12","article-title":"Deep voice: Real-time neural text-to-speech","author":"arik","year":"2017","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683130"},{"key":"ref14","first-page":"483","article-title":"Stacked hourglass networks for human pose estimation","author":"newell","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"WaveNet: A generative model for raw audio","year":"2016","author":"van den oord","key":"ref16"},{"article-title":"The LJ speech dataset","year":"2017","author":"ito","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref19","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-53547-0_25"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1672"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462603"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2468583"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081412"},{"key":"ref9","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2014-191"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/8883092\/08892499.pdf?arnumber=8892499","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:16:20Z","timestamp":1657746980000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8892499\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":24,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/lsp.2019.2951894","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2019,12]]}}}