{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T04:05:46Z","timestamp":1778299546244,"version":"3.51.4"},"reference-count":22,"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":[{"name":"National Key Research and Development Program of China","award":["2017YFB1002102"],"award-info":[{"award-number":["2017YFB1002102"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/lsp.2020.3025410","type":"journal-article","created":{"date-parts":[[2020,9,21]],"date-time":"2020-09-21T21:10:38Z","timestamp":1600722638000},"page":"1730-1734","source":"Crossref","is-referenced-by-count":9,"title":["Adversarial Feature Learning and Unsupervised Clustering Based Speech Synthesis for Found Data With Acoustic and Textual Noise"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4464-146X","authenticated-orcid":false,"given":"Shan","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8234-0823","authenticated-orcid":false,"given":"Lei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683561"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1824"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref13","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Proc Nat Poisons Inf Service"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054106"},{"key":"ref15","first-page":"6306","article-title":"Neural discrete representation learning","author":"oord","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2904"},{"key":"ref17","article-title":"Deep unsupervised clustering with Gaussian mixture variational autoencoders","author":"dilokthanakul","year":"0","journal-title":"arXiv 1611 02648"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.11.063"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-24"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.01.034"},{"key":"ref2","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref9","article-title":"Disentangling speech and non-speech components for building robust acoustic models from found data","author":"gurunath","year":"2019","journal-title":"arXiv 1909 11727"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref22","article-title":"The interspeech 2020 deep noise suppression challenge: Datasets, subjective testing framework, and challenge results","author":"reddy","year":"2020","journal-title":"arXiv 2005 13981"},{"key":"ref21","article-title":"Phase-aware speech enhancement with deep complex u-Net","author":"choi","year":"0","journal-title":"Proc Int Conf Learn Representations"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/8966529\/09201416.pdf?arnumber=9201416","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:47:49Z","timestamp":1651070869000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9201416\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/lsp.2020.3025410","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}