{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T16:00:48Z","timestamp":1784822448916,"version":"3.55.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/lsp.2021.3089437","type":"journal-article","created":{"date-parts":[[2021,6,15]],"date-time":"2021-06-15T19:39:07Z","timestamp":1623785947000},"page":"1265-1269","source":"Crossref","is-referenced-by-count":172,"title":["Towards End-to-End Synthetic Speech Detection"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5184-4359","authenticated-orcid":false,"given":"Guang","family":"Hua","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5063-9484","authenticated-orcid":false,"given":"Andrew Beng Jin","family":"Teoh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8314-6563","authenticated-orcid":false,"given":"Haijian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref38","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2341"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref30","first-page":"6354","article-title":"Replay and synthetic speech detection with Res2Net architecture","author":"li","year":"2021","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref37","first-page":"2037","article-title":"ASVspoof 2015: The first automatic speaker verification spoofing and countermeasures challenge","author":"wu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref35","article-title":"Deep residual learning for image recognition","author":"he","year":"2015","journal-title":"arXiv 1512 03385"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS.2017.8272715"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2016.2647201"},{"key":"ref40","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2684705"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2694139"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.01.001"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.10.001"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2946897"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820738"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2743340"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2771947"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2956589"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2892"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1794"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2723721"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2015.2398812"},{"key":"ref29","first-page":"1033","article-title":"STC antispoofing systems for the ASVspoof 2019 challenge","author":"lavrentyeva","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref5","first-page":"100\ufffd19","article-title":"Neural voice cloning with a few samples","author":"ar?k","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.04.001"},{"key":"ref7","first-page":"2087","article-title":"A comparison of features for synthetic speech detection","author":"sahidullah","year":"0","journal-title":"Proc INTERSPEECH 14th Annu Conf Int Speech Commun Assoc"},{"key":"ref2","first-page":"1","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2682788"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2016.2647199"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053086"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1085"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1887"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101105"},{"key":"ref41","first-page":"1","article-title":"Mixup: Beyond empirical risk minimization","author":"zhang","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.10.007"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-92627-8_16"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2505"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952516"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2732162"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/9325893\/09456037.pdf?arnumber=9456037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T20:36:12Z","timestamp":1635798972000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9456037\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/lsp.2021.3089437","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}