{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:10:23Z","timestamp":1771611023931,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006754","name":"Army Research Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012338","name":"Alan Turing Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012338","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413760","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6159-6163","source":"Crossref","is-referenced-by-count":21,"title":["FoolHD: Fooling Speaker Identification by Highly Imperceptible Adversarial Disturbances"],"prefix":"10.1109","author":[{"given":"Ali Shahin","family":"Shamsabadi","sequence":"first","affiliation":[]},{"given":"Francisco Sepulveda","family":"Teixeira","sequence":"additional","affiliation":[]},{"given":"Alberto","family":"Abad","sequence":"additional","affiliation":[]},{"given":"Bhiksha","family":"Raj","sequence":"additional","affiliation":[]},{"given":"Andrea","family":"Cavallaro","sequence":"additional","affiliation":[]},{"given":"Isabel","family":"Trancoso","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3376897.3377856"},{"key":"ref11","article-title":"Universal adversarial perturbations generative net-work for speaker recognition","author":"li","year":"2020","journal-title":"Proc of the IEEE International Conference on Multimedia and Expo (ICME)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1955"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2380"},{"key":"ref15","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164954"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2250963"},{"key":"ref18","article-title":"Perceptual phase redundancy in speech","author":"kim","year":"2000","journal-title":"Proc of the IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref19","first-page":"286","article-title":"Mel frequency cepstral coefficients: An evaluation of robustness of mp3 encoded music","author":"sigurdsson","year":"2006","journal-title":"International Society for Music Information Retrieval Conference (ISMIR)"},{"key":"ref28","article-title":"A differentiable perceptual audio met-ric learned from just noticeable differences","author":"manocha","year":"2020","journal-title":"Proc of Inter-speech"},{"key":"ref4","article-title":"The faults in our ASRs: An overview of attacks against automatic speech recognition and speaker identification systems","author":"abdullah","year":"2020","journal-title":"Proc of the IEEE Symposium on Security and Privacy"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref3","article-title":"Intriguing properties of neural networks","author":"szegedy","year":"2014","journal-title":"Proc of the International Conference on Learning Representations (ICLR)"},{"key":"ref6","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2015","journal-title":"Proc International Conference on Learning Representations (ICLR)"},{"key":"ref5","article-title":"Adversarial attack and defense strategies for deep speaker recognition systems","author":"jati","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462693"},{"key":"ref7","article-title":"Adversarial examples in the physical world","author":"kurakin","year":"2017","journal-title":"Proc of the International Conference on Learning Representations (ICLR) Workshop Track"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2896880"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053076"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2019.05.009"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref22","article-title":"Voxceleb: A large-scale speaker identification dataset","author":"nagrani","year":"0","journal-title":"Proc of Inter-speech"},{"key":"ref21","article-title":"Adversarial machine learning at scale","author":"kurakin","year":"2017","journal-title":"Proc of the International Conference on Learning Representations (ICLR)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053747"},{"key":"ref23","article-title":"Adversarial attack and defense strategies for deep speaker recognition systems","author":"jati","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref25","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413760.pdf?arnumber=9413760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:53Z","timestamp":1652197253000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413760\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413760","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}