{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:45Z","timestamp":1775229945431,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210096","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Generalized Audio Deepfake Detection Using Frame-level Latent Information Entropy"],"prefix":"10.1109","author":[{"given":"Botao","family":"Zhao","sequence":"first","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zuheng","family":"Kang","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yayun","family":"He","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyang","family":"Qu","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junqing","family":"Peng","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianzong","family":"Wang","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746875"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3530270"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613800"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447923"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658086"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29929"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448095"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref11","article-title":"Audio deepfake detection: A survey","author":"Yi","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446560"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446270"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1383"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ab3430"},{"key":"ref17","article-title":"Information bottleneck for gaussian variables","volume":"16","author":"Chechik","year":"2003","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","article-title":"Deep variational information bottleneck","volume-title":"International Conference on Learning Representations","author":"Alemi"},{"key":"ref19","article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework","volume":"3","author":"Higgins","year":"2017","journal-title":"ICLR (Poster)"},{"key":"ref20","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref22","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":"Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747605"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746213"},{"key":"ref26","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref27","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref28","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International conference on machine learning","author":"Nichol"},{"key":"ref29","article-title":"Pseudo numerical methods for diffusion models on manifolds","volume-title":"International Conference on Learning Representations","author":"Liu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02051"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210096.pdf?arnumber=11210096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:48:11Z","timestamp":1761889691000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210096\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210096","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}