{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:26:24Z","timestamp":1776889584263,"version":"3.51.2"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62101553,62306316,U21B20210,62201571"],"award-info":[{"award-number":["62101553,62306316,U21B20210,62201571"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800375","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"481-485","source":"Crossref","is-referenced-by-count":2,"title":["Does Current Deepfake Audio Detection Model Effectively Detect ALM-Based Deepfake Audio?"],"prefix":"10.1109","author":[{"given":"Yuankun","family":"Xie","sequence":"first","affiliation":[{"name":"Communication University of China,State Key Laboratory of Media Convergence and Communication"}]},{"given":"Chenxu","family":"Xiong","sequence":"additional","affiliation":[{"name":"SDU-ANU Joint Science College, Shandong University,Weihai"}]},{"given":"Xiaopeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences"}]},{"given":"Zhiyong","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences"}]},{"given":"Yi","family":"Lu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences"}]},{"given":"Xin","family":"Qi","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences"}]},{"given":"Ruibo","family":"Fu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences"}]},{"given":"Yukun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences"}]},{"given":"Zhengqi","family":"Wen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing National Research Center for Information Science and Technology"}]},{"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation"}]},{"given":"Guanjun","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences"}]},{"given":"Long","family":"Ye","sequence":"additional","affiliation":[{"name":"Communication University of China,State Key Laboratory of Media Convergence and Communication"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref2","article-title":"Audiogen: Textually guided audio generation","volume-title":"The Eleventh International Conference on Learning Representations","author":"Kreuk","year":"2022"},{"key":"ref3","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Viola: Unified codec language models for speech recognition, synthesis, and translation","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Simple and controllable music generation","volume":"36","author":"Copet","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"Speechx: Neural codec language model as a versatile speech transformer","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Lauragpt: Listen, attend, understand, and regenerate audio with gpt","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Uniaudio: An audio foundation model toward universal audio generation","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Vall-e 2: Neural codec language models are human parity zero-shot text to speech synthesizers","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2022-16"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1383"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1686"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1851"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3324724"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2021.3059479"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"ref19","article-title":"The codecfake dataset and counter-measures for the universally detection of deepfake audio","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Ella-v: Stable neural codec language modeling with alignment-guided sequence reordering","author":"Song","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Ham-tts: Hierarchical acoustic modeling for token-based zero-shot text-to-speech with model and data scaling","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Rall-e: Robust codec language modeling with chain-of-thought prompting for text-to-speech syn-thesis","author":"Xin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Naturalspeech 3: Zero-shot speech syn-thesis with factorized codec and diffusion models","author":"Ju","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Towards generalisable and calibrated synthetic speech detection with self-supervised representations","author":"Oneata","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11460"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1768"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","location":"Beijing, China","start":{"date-parts":[[2024,11,7]]},"end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800375.pdf?arnumber=10800375","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T19:28:29Z","timestamp":1736969309000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800375\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800375","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}