{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:11:08Z","timestamp":1775200268594,"version":"3.50.1"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434771","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Towards Generalized Source Tracing for Codec-Based Deepfake Speech"],"prefix":"10.1109","author":[{"given":"I-Ming","family":"Lin","sequence":"first","affiliation":[{"name":"National Taiwan University,Department of Computer Science and Information Engineering"}]},{"given":"Xuanjun","family":"Chen","sequence":"additional","affiliation":[{"name":"National Taiwan University,Department of Computer Science and Information Engineering"}]},{"given":"Lin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing"}]},{"given":"Haibin","family":"Wu","sequence":"additional","affiliation":[{"name":"Independent Researcher"}]},{"given":"Hung-yi","family":"Lee","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communications Engineering, National Taiwan University"}]},{"given":"Jyh-Shing Roger","family":"Jang","sequence":"additional","affiliation":[{"name":"National Taiwan University,Department of Computer Science and Information Engineering"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3714458"},{"key":"ref2","article-title":"The defender\u2019s perspective on automatic speaker verification: An overview","author":"Wu","year":"2023","journal-title":"arXiv preprint arXiv:2305.12804"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-462"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1111"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2249"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"ref9","article-title":"Add 2023: Towards audio deepfake detection and analysis in the wild","author":"Yi","year":"2024","journal-title":"arXiv preprint arXiv:2408.04967"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1186\/s13635-021-00116-3"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3552466.3556525"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-8367-0_16"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980129"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1283"},{"key":"ref15","article-title":"On the landscape of spoken language models: A comprehensive survey","author":"Arora","year":"2025","journal-title":"arXiv preprint arXiv:2504.08528"},{"key":"ref16","article-title":"Neural codec source tracing: Toward comprehensive attribution in open-set condition","author":"Xie","year":"2025","journal-title":"arXiv preprint arXiv:2501.06514"},{"key":"ref17","article-title":"Towards explainable spoofed speech attribution and detection: a probabilistic approach for characterizing speech synthesizer components","author":"Mishra","year":"2025","journal-title":"arXiv preprint arXiv:2502.04049"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1490"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-16"},{"key":"ref20","article-title":"Towards neural audio codec source parsing","author":"Phukan","year":"2025","journal-title":"arXiv preprint arXiv:2506.12627"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2093"},{"key":"ref22","article-title":"CodecFake+: A large-scale neural audio codec-based deepfake speech dataset","author":"Chen","year":"2025","journal-title":"arXiv preprint arXiv:2501.08238"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1297"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3643619"},{"key":"ref25","article-title":"Towards audio language modeling-an overview","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv:2402.13236"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.616"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832364"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1537"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref30","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref32","first-page":"28","article-title":"Masked autoencoders that listen","volume":"35","author":"Huang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01553"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746900"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1191"},{"key":"ref36","article-title":"Towards out-of-distribution detection in vocoder recognition via latent feature reconstruction","author":"Du","year":"2024","journal-title":"arXiv preprint arXiv:2406.02233"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022646"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10446372"},{"key":"ref39","article-title":"Localizing audiovisual deepfakes via hierarchical boundary modeling","author":"Chen","year":"2025","journal-title":"arXiv preprint arXiv:2508.02000"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","article-title":"Auxiliary tasks in multi-task learning","author":"Liebel","year":"2018","journal-title":"arXiv preprint arXiv:1805.06334"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-16"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746213"},{"key":"ref44","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref45","article-title":"UniAudio: Towards universal audio generation with large language models","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Yang"},{"key":"ref46","article-title":"MaskGCT: Zero-shot text-to-speech with masked generative codec transformer","volume-title":"Proc. ICLR","author":"Wang"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3306711"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1281"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1851"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434771.pdf?arnumber=11434771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:36Z","timestamp":1775192376000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434771","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}