{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:28:49Z","timestamp":1776886129818,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T00:00:00Z","timestamp":1682812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Funding for Postdoctoral Scientific Research Projects in Zhejiang Province","award":["ZJ2021139"],"award-info":[{"award-number":["ZJ2021139"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172359, 61972348, 62102354"],"award-info":[{"award-number":["62172359, 61972348, 62102354"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2021FZZX001-27"],"award-info":[{"award-number":["2021FZZX001-27"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017132","name":"Research Institute of Cyberspace Governance in Zhejiang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017132","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,30]]},"DOI":"10.1145\/3543507.3583222","type":"proceedings-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T23:30:51Z","timestamp":1682551851000},"page":"2033-2044","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":30,"title":["Transferring Audio Deepfake Detection Capability across Languages"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0921-8869","authenticated-orcid":false,"given":"Zhongjie","family":"Ba","sequence":"first","affiliation":[{"name":"Zhejiang University, China and ZJU-Hangzhou Global Scientific and Technological Innovation Center, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8967-3460","authenticated-orcid":false,"given":"Qing","family":"Wen","sequence":"additional","affiliation":[{"name":"Zhejiang University, China and ZJU-Hangzhou Global Scientific and Technological Innovation Center, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4453-2274","authenticated-orcid":false,"given":"Peng","family":"Cheng","sequence":"additional","affiliation":[{"name":"Zhejiang University, China and ZJU-Hangzhou Global Scientific and Technological Innovation Center, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3665-6311","authenticated-orcid":false,"given":"Yuwei","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University, China and ZJU-Hangzhou Global Scientific and Technological Innovation Center, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5240-5200","authenticated-orcid":false,"given":"Feng","family":"Lin","sequence":"additional","affiliation":[{"name":"Zhejiang University, China and ZJU-Hangzhou Global Scientific and Technological Innovation Center, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5230-3749","authenticated-orcid":false,"given":"Li","family":"Lu","sequence":"additional","affiliation":[{"name":"Zhejiang University, China and ZJU-Hangzhou Global Scientific and Technological Innovation Center, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7981-9873","authenticated-orcid":false,"given":"Zhenguang","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University, China and ZJU-Hangzhou Global Scientific and Technological Innovation Center, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"CNN Detection of GAN-Generated Face Images based on Cross-Band Co-occurrences Analysis. CoRR abs\/2007.12909","author":"Barni Mauro","year":"2020","unstructured":"Mauro Barni, Kassem Kallas, Ehsan Nowroozi, and Benedetta Tondi. 2020. CNN Detection of GAN-Generated Face Images based on Cross-Band Co-occurrences Analysis. CoRR abs\/2007.12909 (2020). arXiv:2007.12909https:\/\/arxiv.org\/abs\/2007.12909"},{"key":"e_1_3_2_2_2_1","unstructured":"Berlitz. 2021. The most spoken languages in the world. https:\/\/www.berlitz.com\/blog\/most-spoken-languages-world."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682064"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-5"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"e_1_3_2_2_6_1","volume-title":"The DeepFake Detection Challenge Dataset. CoRR abs\/2006.07397","author":"Dolhansky Brian","year":"2020","unstructured":"Brian Dolhansky, Joanna Bitton, Ben Pflaum, Jikuo Lu, Russ Howes, Menglin Wang, and Cristian Canton-Ferrer. 2020. The DeepFake Detection Challenge Dataset. CoRR abs\/2006.07397 (2020). arXiv:2006.07397https:\/\/arxiv.org\/abs\/2006.07397"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525242"},{"key":"e_1_3_2_2_8_1","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2). https:\/\/openreview.net\/forum?id=74TZg9gsO8W","author":"Frank Joel","year":"2021","unstructured":"Joel Frank and Lea Sch\u00f6nherr. 2021. WaveFake: A Data Set to Facilitate Audio Deepfake Detection. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2). https:\/\/openreview.net\/forum?id=74TZg9gsO8W"},{"key":"e_1_3_2_2_9_1","volume-title":"International conference on machine learning. PMLR, 1180\u20131189","author":"Ganin Yaroslav","year":"2015","unstructured":"Yaroslav Ganin and Victor Lempitsky. 2015. Unsupervised domain adaptation by backpropagation. In International conference on machine learning. PMLR, 1180\u20131189."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3089437"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3141262"},{"key":"e_1_3_2_2_12_1","unstructured":"Junguang Jiang Yang Shu Jianmin Wang and Mingsheng Long. 2022. Transferability in Deep Learning: A Survey. arxiv:2201.05867\u00a0[cs.LG]"},{"key":"e_1_3_2_2_13_1","volume-title":"DeeperForensics Challenge 2020 on Real-World Face Forgery Detection: Methods and Results. CoRR abs\/2102.09471","author":"Jiang Liming","year":"2021","unstructured":"Liming Jiang, Zhengkui Guo, Wayne Wu, Zhaoyang Liu, Ziwei Liu, Chen\u00a0Change Loy, Shuo Yang, Yuanjun Xiong, Wei Xia, Baoying Chen, Peiyu Zhuang, Sili Li, Shen Chen, Taiping Yao, Shouhong Ding, Jilin Li, Feiyue Huang, Liujuan Cao, Rongrong Ji, Changlei Lu, and Ganchao Tan. 2021. DeeperForensics Challenge 2020 on Real-World Face Forgery Detection: Methods and Results. CoRR abs\/2102.09471 (2021). arXiv:2102.09471https:\/\/arxiv.org\/abs\/2102.09471"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01606-8"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01606-8"},{"key":"e_1_3_2_2_16_1","volume-title":"AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks. In arXiv e-prints.","author":"Jung W.","year":"2021","unstructured":"J.\u00a0W. Jung, H.\u00a0S. Heo, H. Tak, H.\u00a0J. Shim, J\u00a0Son Chung, B.\u00a0J. Lee, H.\u00a0J. Yu, and N. Evans. 2021. AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks. In arXiv e-prints."},{"key":"e_1_3_2_2_17_1","volume-title":"Improved rawnet with feature map scaling for text-independent speaker verification using raw waveforms. arXiv preprint arXiv:2004.00526","author":"Ha-Jin Yu.","year":"2020","unstructured":"Jee-weon Jung, Seung-bin Kim, Hye-jin Shim, Ju-ho Kim, and Ha-Jin Yu. 2020. Improved rawnet with feature map scaling for text-independent speaker verification using raw waveforms. arXiv preprint arXiv:2004.00526 (2020)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-16"},{"key":"e_1_3_2_2_19_1","volume-title":"Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detection. arXiv preprint arXiv:2206.13979","author":"Kawa Piotr","year":"2022","unstructured":"Piotr Kawa, Marcin Plata, and Piotr Syga. 2022. Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detection. arXiv preprint arXiv:2206.13979 (2022)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1111"},{"key":"e_1_3_2_2_21_1","volume-title":"Channel-wise gated res2net: Towards robust detection of synthetic speech attacks. arXiv preprint arXiv:2107.08803","author":"Li Xu","year":"2021","unstructured":"Xu Li, Xixin Wu, Hui Lu, Xunying Liu, and Helen Meng. 2021. Channel-wise gated res2net: Towards robust detection of synthetic speech attacks. arXiv preprint arXiv:2107.08803 (2021)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.03.005"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","unstructured":"Weiwei Lin Man-Mai Mak Na Li Dan Su and Dong Yu. 2020. Multi-Level Deep Neural Network Adaptation for Speaker Verification Using MMD and Consistency Regularization. In ICASSP 2020 - 2020 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP). 6839\u20136843. https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9054134","DOI":"10.1109\/ICASSP40776.2020.9054134"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030499"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","unstructured":"Zhenguang Liu Sifan Wu Chejian Xu Xiang Wang Lei Zhu Shuang Wu and Fuli Feng. 2022. Copy Motion From One to Another: Fake Motion Video Generation. In IJCAI. 1223\u20131231. https:\/\/doi.org\/10.24963\/ijcai.2022\/171","DOI":"10.24963\/ijcai.2022"},{"key":"e_1_3_2_2_26_1","volume-title":"Proceedings of the 32nd International Conference on International Conference on Machine Learning -","volume":"37","author":"Long Mingsheng","year":"2015","unstructured":"Mingsheng Long, Yue Cao, Jianmin Wang, and Michael\u00a0I. Jordan. 2015. Learning Transferable Features with Deep Adaptation Networks. In Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37 (Lille, France) (ICML\u201915). JMLR.org, 97\u2013105."},{"key":"e_1_3_2_2_27_1","unstructured":"Mingsheng Long Han Zhu Jianmin Wang and Michael\u00a0I. Jordan. 2017. Deep Transfer Learning with Joint Adaptation Networks(ICML\u201917). JMLR.org 2208\u20132217."},{"key":"e_1_3_2_2_28_1","volume-title":"International conference on machine learning. PMLR, 2208\u20132217","author":"Long Mingsheng","year":"2017","unstructured":"Mingsheng Long, Han Zhu, Jianmin Wang, and Michael\u00a0I Jordan. 2017. Deep transfer learning with joint adaptation networks. In International conference on machine learning. PMLR, 2208\u20132217."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-72"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","unstructured":"Tanvina\u00a0B Patel and Hemant\u00a0A Patil. 2015. Combining evidences from mel cepstral cochlear filter cepstral and instantaneous frequency features for detection of natural vs. spoofed speech. In Sixteenth annual conference of the international speech communication association.","DOI":"10.21437\/Interspeech.2015-467"},{"key":"e_1_3_2_2_32_1","volume-title":"International Conference on Machine Learning. PMLR, 2988\u20132997","author":"Saito Kuniaki","year":"2017","unstructured":"Kuniaki Saito, Yoshitaka Ushiku, and Tatsuya Harada. 2017. Asymmetric tri-training for unsupervised domain adaptation. In International Conference on Machine Learning. PMLR, 2988\u20132997."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10306"},{"key":"e_1_3_2_2_35_1","volume-title":"End-to-end spectro-temporal graph attention networks for speaker verification anti-spoofing and speech deepfake detection. arXiv preprint arXiv:2107.12710","author":"Tak Hemlata","year":"2021","unstructured":"Hemlata Tak, Jee-weon Jung, Jose Patino, Madhu Kamble, Massimiliano Todisco, and Nicholas Evans. 2021. End-to-end spectro-temporal graph attention networks for speaker verification anti-spoofing and speech deepfake detection. arXiv preprint arXiv:2107.12710 (2021)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"e_1_3_2_2_37_1","volume-title":"A survey on neural speech synthesis. arXiv preprint arXiv:2106.15561","author":"Tan Xu","year":"2021","unstructured":"Xu Tan, Tao Qin, Frank Soong, and Tie-Yan Liu. 2021. A survey on neural speech synthesis. arXiv preprint arXiv:2106.15561 (2021)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512212"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.01.001"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"crossref","unstructured":"Massimiliano Todisco H\u00e9ctor Delgado and Nicholas\u00a0WD Evans. 2016. A New Feature for Automatic Speaker Verification Anti-Spoofing: Constant Q Cepstral Coefficients.. In Odyssey Vol.\u00a02016. 283\u2013290.","DOI":"10.21437\/Odyssey.2016-41"},{"key":"e_1_3_2_2_41_1","volume-title":"ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection. arXiv preprint arXiv:1904.05441","author":"Todisco Massimiliano","year":"2019","unstructured":"Massimiliano Todisco, Xin Wang, Ville Vestman, Md Sahidullah, Hector Delgado, Andreas Nautsch, Junichi Yamagishi, Nicholas Evans, Tomi Kinnunen, and Kong\u00a0Aik Lee. 2019. ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection. arXiv preprint arXiv:1904.05441 (2019)."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"e_1_3_2_2_43_1","volume-title":"Visualizing data using t-SNE.Journal of machine learning research 9, 11","author":"Maaten Laurens Van\u00a0der","year":"2008","unstructured":"Laurens Van\u00a0der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE.Journal of machine learning research 9, 11 (2008)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1255"},{"key":"e_1_3_2_2_45_1","volume-title":"A comparative study on recent neural spoofing countermeasures for synthetic speech detection. arXiv preprint arXiv:2103.11326","author":"Wang Xin","year":"2021","unstructured":"Xin Wang and Junich Yamagishi. 2021. A comparative study on recent neural spoofing countermeasures for synthetic speech detection. arXiv preprint arXiv:2103.11326 (2021)."},{"key":"e_1_3_2_2_46_1","volume-title":"Investigating self-supervised front ends for speech spoofing countermeasures. arXiv preprint arXiv:2111.07725","author":"Wang Xin","year":"2021","unstructured":"Xin Wang and Junichi Yamagishi. 2021. Investigating self-supervised front ends for speech spoofing countermeasures. arXiv preprint arXiv:2111.07725 (2021)."},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3130975"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10312"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3400066"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-462"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682259"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"crossref","unstructured":"Yang Xie Zhenchuan Zhang and Yingchun Yang. 2021. Siamese Network with wav2vec Feature for Spoofing Speech Detection.. In Interspeech. 4269\u20134273.","DOI":"10.21437\/Interspeech.2021-847"},{"key":"e_1_3_2_2_53_1","volume-title":"ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection. arXiv preprint arXiv:2109.00537","author":"Yamagishi Junichi","year":"2021","unstructured":"Junichi Yamagishi, Xin Wang, Massimiliano Todisco, Md Sahidullah, Jose Patino, Andreas Nautsch, Xuechen Liu, Kong\u00a0Aik Lee, Tomi Kinnunen, Nicholas Evans, 2021. ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection. arXiv preprint arXiv:2109.00537 (2021)."},{"key":"e_1_3_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17280"},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2021.3076358"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1820"},{"key":"e_1_3_2_2_57_1","volume-title":"FMFCC-A: A Challenging Mandarin Dataset for Synthetic Speech Detection. CoRR abs\/2110.09441","author":"Zhang Zhenyu","year":"2021","unstructured":"Zhenyu Zhang, Yewei Gu, Xiaowei Yi, and Xianfeng Zhao. 2021. FMFCC-A: A Challenging Mandarin Dataset for Synthetic Speech Detection. CoRR abs\/2110.09441 (2021). arXiv:2110.09441https:\/\/arxiv.org\/abs\/2110.09441"}],"event":{"name":"WWW '23: The ACM Web Conference 2023","location":"Austin TX USA","acronym":"WWW '23","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583222","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543507.3583222","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:09:18Z","timestamp":1750183758000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583222"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":57,"alternative-id":["10.1145\/3543507.3583222","10.1145\/3543507"],"URL":"https:\/\/doi.org\/10.1145\/3543507.3583222","relation":{},"subject":[],"published":{"date-parts":[[2023,4,30]]},"assertion":[{"value":"2023-04-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}