{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:34Z","timestamp":1775229934673,"version":"3.50.1"},"reference-count":72,"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\/"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Army Research Office and was accomplished under Cooperative","award":["W911NF-20-2-0111"],"award-info":[{"award-number":["W911NF-20-2-0111"]}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency (DARPA) and the Air Force Research Laboratory","doi-asserted-by":"publisher","award":["FA8750-20-2-1004"],"award-info":[{"award-number":["FA8750-20-2-1004"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency (DARPA) and the Air Force Research Laboratory","doi-asserted-by":"publisher","award":["HR001120C0126"],"award-info":[{"award-number":["HR001120C0126"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1553610"],"award-info":[{"award-number":["1553610"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"U.S. Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright notation thereon"},{"name":"PREMIER Project, funded by the Italian Ministry of Education, University, and Research within the PRIN 2017 Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3276480","type":"journal-article","created":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T18:44:46Z","timestamp":1684176286000},"page":"50851-50866","source":"Crossref","is-referenced-by-count":50,"title":["TIMIT-TTS: A Text-to-Speech Dataset for Multimodal Synthetic Media Detection"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5163-3364","authenticated-orcid":false,"given":"Davide","family":"Salvi","sequence":"first","affiliation":[{"name":"Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy"}]},{"given":"Brian","family":"Hosler","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0406-0222","authenticated-orcid":false,"given":"Paolo","family":"Bestagini","sequence":"additional","affiliation":[{"name":"Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy"}]},{"given":"Matthew C.","family":"Stamm","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1990-9869","authenticated-orcid":false,"given":"Stefano","family":"Tubaro","sequence":"additional","affiliation":[{"name":"Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Pennsylvania woman accused of using deepfake technology to harass cheerleaders","year":"2021"},{"key":"ref2","volume-title":"A Zelensky Deepfake was Quickly Defeated. The Next One Might Not Be","year":"2022"},{"key":"ref3","volume-title":"Deepfakes are Now Trying to Change the Course of War","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2120481119"},{"key":"ref5","volume-title":"That Smiling LinkedIn Profile Face Might be a Computer-Generated Fake","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3002101"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3154404"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2905689"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00341"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2988660"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS49906.2020.9360904"},{"key":"ref12","article-title":"The deepfake detection challenge (DFDC) dataset","author":"Dolhansky","year":"2020","journal-title":"arXiv:2006.07397"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2249"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref17","article-title":"DeepFakes: A new threat to face recognition? Assessment and detection","author":"Korshunov","year":"2018","journal-title":"arXiv:1812.08685"},{"key":"ref18","article-title":"WaveFake: A data set to facilitate audio deepfake detection","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Frank"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00112"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/AIPR50011.2020.9425192"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3476099.3484315"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01793-3_21"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412711"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"ref25","article-title":"FakeAVCeleb: A novel audio-video multimodal deepfake dataset","volume-title":"Proc. Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track (Round)","author":"Khalid"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1121\/1.395275"},{"key":"ref28","first-page":"2","article-title":"WaveNet: A generative model for raw audio","volume-title":"Proc. SSW","volume":"125","author":"Oord"},{"key":"ref29","article-title":"NeMo: A toolkit for building AI applications using neural modules","author":"Kuchaiev","year":"2019","journal-title":"arXiv:1909.09577"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2047683"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW46912.2020.9105991"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLC.2011.6016982"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR.2019.00104"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1186\/s13635-021-00116-3"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3231480"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-472"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747186"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-37742-6_21"},{"key":"ref44","volume-title":"Real-Time-Voice-Cloning","author":"Jemine","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref46","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kim"},{"key":"ref47","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv:2006.04558"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"ref49","article-title":"TalkNet: Fully-convolutional non-autoregressive speech synthesis model","author":"Beliaev","year":"2020","journal-title":"arXiv:2005.05514"},{"key":"ref50","article-title":"Mixer-TTS: Non-autoregressive, fast and compact text-to-speech model conditioned on language model embeddings","author":"Tatanov","year":"2021","journal-title":"arXiv:2110.03584"},{"key":"ref51","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2867"},{"key":"ref53","volume-title":"gTTS","author":"Durette","year":"2022"},{"key":"ref54","volume-title":"Silero Models: Pre-Trained Enterprise-Grade STT\/TTS Models and Benchmarks","year":"2021"},{"key":"ref55","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Kumar"},{"key":"ref56","first-page":"2410","article-title":"Efficient neural audio synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kalchbrenner"},{"key":"ref57","volume-title":"The LJ Speech Dataset","author":"Ito","year":"2017"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref59","volume-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413700"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03434"},{"key":"ref62","volume-title":"Audiomentations","author":"Jordal","year":"2022"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.04.005"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01793-3_21"},{"key":"ref65","first-page":"27403","article-title":"DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1-1.1","author":"Garofolo","year":"1993"},{"key":"ref66","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022","journal-title":"arXiv:2212.04356"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-9"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2382"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS55849.2022.9975440"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref72","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6287639\/10005208\/10124769-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10124769.pdf?arnumber=10124769","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T05:14:57Z","timestamp":1709270097000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10124769\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3276480","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}