{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T06:15:13Z","timestamp":1772777713645,"version":"3.50.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688312","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"1178-1184","source":"Crossref","is-referenced-by-count":10,"title":["Using Self Attention DNNs to Discover Phonemic Features for Audio Deep Fake Detection"],"prefix":"10.1109","author":[{"given":"Hira","family":"Dhamyal","sequence":"first","affiliation":[{"name":"Lahore University of Management Sciences"}]},{"given":"Ayesha","family":"Ali","sequence":"additional","affiliation":[{"name":"Lahore University of Management Sciences"}]},{"given":"Ihsan Ayyub","family":"Qazi","sequence":"additional","affiliation":[{"name":"Lahore University of Management Sciences"}]},{"given":"Agha Ali","family":"Raza","sequence":"additional","affiliation":[{"name":"Lahore University of Management Sciences"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1282"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003824"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1794"},{"key":"ref12","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"jie","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref13","first-page":"104","article-title":"Detecting ai-synthesized speech using bispectral analysis","author":"albadawy","year":"0","journal-title":"CVPR Workshops"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-524"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383558"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2684705"},{"key":"ref17","article-title":"Synthetic speech discrimination using pitch pattern statistics derived from image analysis","author":"de leon","year":"0","journal-title":"Thirteenth Annual Conference of the International Speech Communication Association"},{"key":"ref18","article-title":"An attentive survey of attention models","author":"chaudhari","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/S0272263114000151"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9924(94)90010-8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/BF01067922"},{"key":"ref29","first-page":"3543","article-title":"Attention is not explanation","volume":"1","author":"jain","year":"0","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcomdis.2009.07.004"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2999185"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1558\/sll.1999.6.2.265"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MIPRO.2016.7522354"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-19"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/CyCon49761.2020.9131716"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639664"},{"key":"ref22","author":"halpern","year":"0","journal-title":"Residual networks for resisting noise analysis of an embeddings-based spoofing countermeasure"},{"key":"ref21","first-page":"3451","article-title":"The Phonetic Bases of Vocal Expressed Emotion: Natural versus Acted","author":"memon","year":"0","journal-title":"Proc Interspeech 2020"},{"key":"ref24","year":"2019","journal-title":"Asvspoof 2019 the automatic speaker verification spoofing and counter-measures challenge evaluation plan"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-41"},{"key":"ref26","first-page":"2","article-title":"The cmu sphinx-4 speech recognition system","volume":"1","author":"lamere","year":"2003","journal-title":"IEEE Intl Conf on Acoustics Speech and Signal Processing (ICASSP 2003)"},{"key":"ref25","year":"0","journal-title":"Watson speech to text - overview"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688312.pdf?arnumber=9688312","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:42:13Z","timestamp":1652733733000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688312\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688312","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}