{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T03:36:01Z","timestamp":1773200161412,"version":"3.50.1"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"ASEAN IVO"},{"name":"Project, titled Spoof Detection for Automatic Speaker Verification"},{"DOI":"10.13039\/501100012389","name":"National Institute of Information and Communications Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012389","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009105","name":"SCOPE Program of Ministry of Internal Affairs and Communications","doi-asserted-by":"publisher","award":["201605002"],"award-info":[{"award-number":["201605002"]}],"id":[{"id":"10.13039\/501100009105","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011923","name":"KDDI Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011923","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fund for the Promotion of Joint International Research","award":["20KK0233"],"award-info":[{"award-number":["20KK0233"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3301616","type":"journal-article","created":{"date-parts":[[2023,8,3]],"date-time":"2023-08-03T17:40:19Z","timestamp":1691084419000},"page":"84689-84698","source":"Crossref","is-referenced-by-count":13,"title":["Contributions of Jitter and Shimmer in the Voice for Fake Audio Detection"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6633-3954","authenticated-orcid":false,"given":"Kai","family":"Li","sequence":"first","affiliation":[{"name":"Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7075-448X","authenticated-orcid":false,"given":"Xugang","family":"Lu","sequence":"additional","affiliation":[{"name":"Advanced Speech Technology Laboratory, National Institute of Information and Communications Technology, Kyoto, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2450-6754","authenticated-orcid":false,"given":"Masato","family":"Akagi","sequence":"additional","affiliation":[{"name":"Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6605-2052","authenticated-orcid":false,"given":"Masashi","family":"Unoki","sequence":"additional","affiliation":[{"name":"Graduate School of Advanced Science and Technology, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2212"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1187"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2021.3059479"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2833032"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3174"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414670"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1794"},{"key":"ref18","first-page":"1352","article-title":"Densely connected convolutional network for audio spoofing detection","author":"wang","year":"2020","journal-title":"Proc Asia–Pacific Signal Inf Process Assoc Annu Summit Conf (APSIPA ASC)"},{"key":"ref46","article-title":"ASVspoof2021: Accelerating progress in spoofed and deep fake speech detection","author":"yamagishi","year":"2021","journal-title":"arXiv 2109 00537"},{"key":"ref45","first-page":"1","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref48","article-title":"Libf0: A Python library for fundamental frequency estimation","author":"rosenzweig","year":"2022","journal-title":"Proc Late Breaking Demos Int Soc Music Inf Retr Conf (ISMIR)"},{"key":"ref47","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","article-title":"Network in network","author":"lin","year":"2013","journal-title":"arXiv 1312 4400"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10088"},{"key":"ref44","article-title":"ADD 2023: The second audio deepfake detection challenge","author":"yi","year":"2023","journal-title":"arXiv 2305 13774"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2811740"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-702"},{"key":"ref7","article-title":"Investigating self-supervised front ends for speech spoofing countermeasures","author":"wang","year":"2021","journal-title":"arXiv 2111 07725"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1810"},{"key":"ref4","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry-ryan","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref6","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020","journal-title":"arXiv 2006 04558"},{"key":"ref5","first-page":"3171","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume":"32","author":"ren","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-360"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1121\/1.2951592"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853678"},{"key":"ref37","author":"baken","year":"2000","journal-title":"Clinical Measurement of Speech and Voice"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980028"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/000348949610500503"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1177\/000348949410300211"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1121\/1.1458024"},{"key":"ref32","first-page":"2787","article-title":"Instantaneous pitch estimation based on RAPT framework","author":"azarov","year":"2012","journal-title":"Proc 20th Eur Signal Process Conf (EUSIPCO)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"ref39","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1121\/1.4939739"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2723"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.01.001"},{"key":"ref26","first-page":"640","article-title":"The prosody of speech: Melody and rhythm","volume":"5","author":"nooteboom","year":"1997","journal-title":"The Handbook of Phonetic Sciences"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-022-02126-z"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2289"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2019.21"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/SPA.2019.8936657"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.3606.1120"},{"key":"ref29","first-page":"700","article-title":"Glottal-to-noise excitation ratio—A new measure for describing pathological voices","volume":"83","author":"michaelis","year":"1997","journal-title":"Acta Acustica United with Acustica"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10207023.pdf?arnumber=10207023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T18:19:07Z","timestamp":1693851547000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10207023\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3301616","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}