{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:27:22Z","timestamp":1775230042384,"version":"3.50.1"},"reference-count":37,"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\/501100003803","name":"University of Hong Kong","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003803","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\/icassp43922.2022.9746162","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"9236-9240","source":"Crossref","is-referenced-by-count":25,"title":["Partially Fake Audio Detection by Self-Attention-Based Fake Span Discovery"],"prefix":"10.1109","author":[{"given":"Haibin","family":"Wu","sequence":"first","affiliation":[{"name":"National Taiwan University,Graduate Institute of Communication Engineering"}]},{"given":"Heng-Cheng","family":"Kuo","sequence":"additional","affiliation":[{"name":"Academia Sinica,Research Center for Information Technology Innovation,Taiwan"}]},{"given":"Naijun","family":"Zheng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Human-Computer Communications Laboratory"}]},{"given":"Kuo-Hsuan","family":"Hung","sequence":"additional","affiliation":[{"name":"Academia Sinica,Research Center for Information Technology Innovation,Taiwan"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University,Graduate Institute of Communication Engineering"}]},{"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[{"name":"Academia Sinica,Research Center for Information Technology Innovation,Taiwan"}]},{"given":"Hsin-Min","family":"Wang","sequence":"additional","affiliation":[{"name":"Academia Sinica,Institute of Information Science,Taiwan"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Centre for Perceptual and Interactive Intelligence"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref31","article-title":"Aishell-3: A multispeaker mandarin tts corpus and the baselines","author":"shi","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref37","article-title":"Pulse code modulation (pcm) of voice frequencies","author":"recommendation","year":"1988","journal-title":"ITU"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref35","article-title":"Musan: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003763"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413828"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2125"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1452"},{"key":"ref14","article-title":"Improving the adversarial robustness for speaker verification by self-supervised learning","author":"wu","year":"2021"},{"key":"ref15","article-title":"Spotting adversarial samples for speaker verification by neural vocoders","author":"wu","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.10.005"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2014.7041636"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2019.21"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053086"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-8"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2026"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"1517","DOI":"10.21437\/Interspeech.2017-1575","article-title":"Deep speaker embeddings for short-duration speaker verification","author":"bhattacharya","year":"2017","journal-title":"InterSpeech"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1343"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053643"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1111","article-title":"The asvspoof 2017 challenge: Assessing the limits of replay spoofing attack detection","author":"kinnunen","year":"2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413737"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-462"},{"key":"ref20","article-title":"Global and temporalfrequency attention based network in audio deepfake detection","author":"chenglong","year":"2021","journal-title":"Journal of Computer research and development"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-930"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-794"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"82","DOI":"10.21437\/Interspeech.2017-360","article-title":"Audio replay attack detection with deep learning frameworks","author":"lavrentyeva","year":"2017","journal-title":"InterSpeech"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-702"},{"key":"ref26","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"Assert: Antispoofing with squeeze-excitation and residual networks","author":"lai","year":"2019"}],"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\/09746162.pdf?arnumber=9746162","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:10:22Z","timestamp":1660594222000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746162\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746162","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}