{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T02:32:52Z","timestamp":1781922772008,"version":"3.54.5"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006602","name":"Air Force Research Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006602","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747186","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8962-8966","source":"Crossref","is-referenced-by-count":57,"title":["Deepfake Speech Detection Through Emotion Recognition: A Semantic Approach"],"prefix":"10.1109","author":[{"given":"Emanuele","family":"Conti","sequence":"first","affiliation":[{"name":"Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria,Milan,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Davide","family":"Salvi","sequence":"additional","affiliation":[{"name":"Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria,Milan,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Clara","family":"Borrelli","sequence":"additional","affiliation":[{"name":"Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria,Milan,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian","family":"Hosler","sequence":"additional","affiliation":[{"name":"Drexel University,Department of Electrical and Computer Engineering,Philadelphia,PA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paolo","family":"Bestagini","sequence":"additional","affiliation":[{"name":"Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria,Milan,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabio","family":"Antonacci","sequence":"additional","affiliation":[{"name":"Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria,Milan,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Augusto","family":"Sarti","sequence":"additional","affiliation":[{"name":"Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria,Milan,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew C.","family":"Stamm","sequence":"additional","affiliation":[{"name":"Drexel University,Department of Electrical and Computer Engineering,Philadelphia,PA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefano","family":"Tubaro","sequence":"additional","affiliation":[{"name":"Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria,Milan,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2019.21"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1186\/s13635-021-00116-3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS53200.2021.9648389"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00112"},{"key":"ref14","article-title":"Emotions Don’t Lie: An Audio-Visual Deepfake Detection Method using Affective Cues","author":"mittal","year":"0"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2936124"},{"key":"ref17","article-title":"Multimodal utterance-level affect analysis using visual, audio and text features","author":"deng","year":"2018","journal-title":"CoRR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.134"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref4","article-title":"The malicious use of artificial intelligence: Forecasting, prevention, and mitigation","author":"brundage","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"ref3","article-title":"Deepfake app causes fraud and privacy fears in china","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00338"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3002101"},{"key":"ref8","article-title":"Hello? Who Am I Talking to?","author":"lieto","year":"2019","journal-title":"A shallow CNN approach for human vs bot speech classification \" in IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412711"},{"key":"ref2","author":"howcroft","year":"2018","journal-title":"How Faking Videos Became EasyÂ?and why that’s so Scary"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-19"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929475"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1080\/09515080903153600"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","article-title":"IEMOCAP: Interactive emotional dyadic motion capture database","volume":"42","author":"busso","year":"2008","journal-title":"Language Resources and Evaluation"},{"key":"ref23","article-title":"The LJSpeech dataset","author":"ito","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref25","article-title":"CNN architectures for largescale audio classification","author":"hershey","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747186.pdf?arnumber=9747186","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:08:54Z","timestamp":1660594134000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747186\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747186","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}