{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:50:43Z","timestamp":1780588243995,"version":"3.54.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095927","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":40,"title":["BTS-E: Audio Deepfake Detection Using Breathing-Talking-Silence Encoder"],"prefix":"10.1109","author":[{"given":"Thien-Phuc","family":"Doan","sequence":"first","affiliation":[{"name":"Soongsil University,School of Electronic Engineering,Seoul,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Nguyen-Vu","sequence":"additional","affiliation":[{"name":"Soongsil University,School of Electronic Engineering,Seoul,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Souhwan","family":"Jung","sequence":"additional","affiliation":[{"name":"Soongsil University,School of Electronic Engineering,Seoul,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kihun","family":"Hong","sequence":"additional","affiliation":[{"name":"Soongsil University,School of Electronic Engineering,Seoul,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3089437"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-19"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11029"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-438"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"ref2","article-title":"A survey on neural speech synthesis","author":"tan","year":"2021"},{"key":"ref1","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.01.008"},{"key":"ref16","article-title":"A statistical model-based voice activity detection","volume":"6","author":"sohn","year":"1999","journal-title":"IEEE Signal Processing Letters"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2006.1706829"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE-TW52618.2021.9603163"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/sym13020214"},{"key":"ref23","article-title":"Audio replay spoofing attack detection using deep learning feature and long-short-term memory recurrent neural network","author":"huang","year":"2021","journal-title":"Proc AIIPCC"},{"key":"ref26","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2022","journal-title":"Proc ICLR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10200"},{"key":"ref20","article-title":"Attentional feature fusion","author":"dai","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10271"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-13"},{"key":"ref27","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","article-title":"ASVspoof 2021: accelerating progress in spoofed and deep-fake speech detection","author":"yamagishi","year":"2021","journal-title":"Proc 2021 Edition of the ASVSpoof Challenge"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-702"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.7439\/ijasr.v1i7.1975"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-92627-8_15"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1111"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-462"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095927.pdf?arnumber=10095927","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T19:49:23Z","timestamp":1777664963000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095927\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095927","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}