{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:44:58Z","timestamp":1776883498579,"version":"3.51.2"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448453","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10581-10585","source":"Crossref","is-referenced-by-count":15,"title":["HM-CONFORMER: A Conformer-Based Audio Deepfake Detection System with Hierarchical Pooling and Multi-Level Classification Token Aggregation Methods"],"prefix":"10.1109","author":[{"given":"Hyun-seo","family":"Shin","sequence":"first","affiliation":[{"name":"University of Seoul,School of Computer Science"}]},{"given":"Jungwoo","family":"Heo","sequence":"additional","affiliation":[{"name":"University of Seoul,School of Computer Science"}]},{"given":"Ju-ho","family":"Kim","sequence":"additional","affiliation":[{"name":"University of Seoul,School of Computer Science"}]},{"given":"Chan-yeong","family":"Lim","sequence":"additional","affiliation":[{"name":"University of Seoul,School of Computer Science"}]},{"given":"Wonbin","family":"Kim","sequence":"additional","affiliation":[{"name":"University of Seoul,School of Computer Science"}]},{"given":"Ha-Jin","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Seoul,School of Computer Science"}]}],"member":"263","reference":[{"key":"ref1","first-page":"7748","article-title":"Meta-stylespeech: Multi-speaker adaptive text-to-speech generation","volume-title":"International Conference on Machine Learning","author":"Min"},{"key":"ref2","first-page":"2709","article-title":"Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone","volume-title":"International Conference on Machine Learning","author":"Casanova"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-702"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096278"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref8","first-page":"4271","article-title":"Funnel-transformer: Filtering out sequential redundancy for efficient language processing","volume":"33","author":"Dai","year":"2020","journal-title":"Neural IPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-12"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1626"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/PRAI55851.2022.9904136"},{"key":"ref12","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of NAACL-HLT","author":"Ming-Wei Chang Kenton"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632794"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413423"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3169954"},{"issue":"1","key":"ref16","first-page":"5","article-title":"Swish: a self-gated activation function","volume":"7","author":"Ramachandran","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00043"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/rs13040731"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746602"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3076358"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3081010"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448453.pdf?arnumber=10448453","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:54:06Z","timestamp":1722660846000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448453\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448453","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}