{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:27:21Z","timestamp":1775230041988,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956134","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"3224-3230","source":"Crossref","is-referenced-by-count":11,"title":["Localizing Fake Segments in Speech"],"prefix":"10.1109","author":[{"given":"Bowen","family":"Zhang","sequence":"first","affiliation":[{"name":"National University of Singapore,School of Computing"}]},{"given":"Terence","family":"Sim","sequence":"additional","affiliation":[{"name":"National University of Singapore,School of Computing"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Asvspoof 2019: The 3rd automatic speaker verification spoofing and countermeasures challenge database","author":"yamagishi","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SPED.2019.8906599"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6044"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-930"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-738"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref18","first-page":"3683","article-title":"Fitting new speakers based on a short untranscribed sample","author":"nachmani","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref19","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020","journal-title":"arXiv preprint arXiv 2006 04989"},{"key":"ref4","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"arXiv preprint arXiv 1703 10593"},{"key":"ref3","first-page":"145","article-title":"Vulnerability of speaker verification to voice mimicking","author":"lau","year":"2004","journal-title":"Proceedings of 2004 International Symposium on Intelligent Multimedia Video and Speech Processing 2004"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"ref5","article-title":"Wavenet: A generative model for raw audio","author":"oord","year":"2016","journal-title":"arXiv preprint arXiv 1609 03286"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-462"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-360"},{"key":"ref2","first-page":"1753","article-title":"Deep fakes: A looming challenge for privacy, democracy, and national security","volume":"107","author":"chesney","year":"2019","journal-title":"Calif Law Review"},{"key":"ref9","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":"ref1","article-title":"Audio deepfake scams: The growing threat explored","author":"noone","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref22","article-title":"40, 32, 24, 16 kbit\/s adaptive differential pulse code modulation(adpcm)","author":"union","year":"1990","journal-title":"ITU-T Recommendation G 726"},{"key":"ref21","article-title":"Pulse code modulation (pcm) of voice frequencies","author":"union","year":"1988","journal-title":"ITU-T Recommendation G 711"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-41"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.01.001"},{"key":"ref26","first-page":"59","article-title":"Length of phonemes in a context of their positions in polish sentences","author":"igras","year":"2013","journal-title":"2013 International Conference on Signal Processing and Multimedia Applications (SIGMAP)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1978.1170547"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","location":"Montreal, QC, Canada","start":{"date-parts":[[2022,8,21]]},"end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956134.pdf?arnumber=9956134","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:07:18Z","timestamp":1671480438000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956134\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956134","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}