{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:43:54Z","timestamp":1772905434947,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":44,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819615476","type":"print"},{"value":"9789819615483","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-1548-3_21","type":"book-chapter","created":{"date-parts":[[2025,2,16]],"date-time":"2025-02-16T09:14:37Z","timestamp":1739697277000},"page":"301-320","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Who is Being Impersonated? Deepfake Audio Detection and\u00a0Impersonated Identification via\u00a0Extraction of\u00a0Id-Specific Features"],"prefix":"10.1007","author":[{"given":"Tianchen","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heming","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huan","family":"Huo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,17]]},"reference":[{"key":"21_CR1","unstructured":"AlGhareeb, S.M.: An exploration of impersonation crimes: new perspectives of confrontational offenders and offenses. Ph.D. thesis, University of Colorado at Denver (2021)"},{"issue":"5","key":"21_CR2","doi-asserted-by":"publisher","first-page":"155","DOI":"10.3390\/a15050155","volume":"15","author":"Z Almutairi","year":"2022","unstructured":"Almutairi, Z., Elgibreen, H.: A review of modern audio deepfake detection methods: challenges and future directions. Algorithms 15(5), 155 (2022)","journal-title":"Algorithms"},{"issue":"1","key":"21_CR3","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1007\/s00530-023-01248-x","volume":"30","author":"S Asha","year":"2024","unstructured":"Asha, S., Vinod, P., Menon, V.G.: A defensive attention mechanism to detect deepfake content across multiple modalities. Multimedia Syst. 30(1), 56 (2024)","journal-title":"Multimedia Syst."},{"key":"21_CR4","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. Adv. Neural Inf. Process. Syst. 33, 12449\u201312460 (2020)"},{"key":"21_CR5","unstructured":"Brooks, T., et al.: Video generation models as world simulators (2024). https:\/\/openai.com\/research\/video-generation-models-as-world-simulators"},{"key":"21_CR6","doi-asserted-by":"publisher","unstructured":"Cao, X., Gong, N.Z.: Understanding the security of deepfake detection. In: Gladyshev, P., Goel, S., James, J., Markowsky, G., Johnson, D. (eds.) Digital Forensics and Cyber Crime, ICDF2C 2021. LNICS, Social Informatics and Telecommunications Engineering, vol. 441, pp. 360\u2013378. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-031-06365-7_22","DOI":"10.1007\/978-3-031-06365-7_22"},{"issue":"1","key":"21_CR7","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1109\/COMST.2020.2969030","volume":"23","author":"M Caprolu","year":"2020","unstructured":"Caprolu, M., Sciancalepore, S., Di Pietro, R.: Short-range audio channels security: survey of mechanisms, applications, and research challenges. IEEE Commun. Surv. Tutorials 23(1), 311\u2013340 (2020)","journal-title":"IEEE Commun. Surv. Tutorials"},{"key":"21_CR8","series-title":"Lecture Notes in Networks and Systems","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1007\/978-981-16-0733-2_39","volume-title":"Proceedings of Second International Conference on Computing, Communications, and Cyber-Security","author":"A Chadha","year":"2021","unstructured":"Chadha, A., Kumar, V., Kashyap, S., Gupta, M.: DeepFake: an overview. In: Singh, P.K., Wierzcho\u0144, S.T., Tanwar, S., Ganzha, M., Rodrigues, J.J.P.C. (eds.) Proceedings of Second International Conference on Computing, Communications, and Cyber-Security. LNNS, vol. 203, pp. 557\u2013566. Springer, Singapore (2021). https:\/\/doi.org\/10.1007\/978-981-16-0733-2_39"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Chakravarty, N., Dua, M.: A lightweight feature extraction technique for deepfake audio detection. Multimedia Tools Appl., 1\u201325 (2024)","DOI":"10.1007\/s11042-024-18217-9"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Nagrani, A., Zisserman, A.: VoxCeleb2: deep speaker recognition. arXiv preprint arXiv:1806.05622 (2018)","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"21_CR11","unstructured":"Cordonnier, J.B., Loukas, A., Jaggi, M.: On the relationship between self-attention and convolutional layers. arXiv preprint arXiv:1911.03584 (2019)"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Dixit, A., Kaur, N., Kingra, S.: Review of audio deepfake detection techniques: issues and prospects. Expert Syst., e13322 (2023)","DOI":"10.1111\/exsy.13322"},{"key":"21_CR13","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian Error Linear Units (GELUs). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"21_CR14","unstructured":"Huang, L., Pun, C.M.: Self-attention and hybrid features for replay and deep-fake audio detection. arXiv preprint arXiv:2401.05614 (2024)"},{"key":"21_CR15","doi-asserted-by":"publisher","first-page":"1001063","DOI":"10.3389\/fdata.2022.1001063","volume":"5","author":"Z Khanjani","year":"2023","unstructured":"Khanjani, Z., Watson, G., Janeja, V.P.: Audio deepfakes: a survey. Front. Big Data 5, 1001063 (2023)","journal-title":"Front. Big Data"},{"key":"21_CR16","first-page":"1","volume":"47","author":"J Khochare","year":"2021","unstructured":"Khochare, J., Joshi, C., Yenarkar, B., Suratkar, S., Kazi, F.: A deep learning framework for audio deepfake detection. Arab. J. Sci. Eng. 47, 1\u201312 (2021)","journal-title":"Arab. J. Sci. Eng."},{"key":"21_CR17","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Li, J., et\u00a0al.: Recent advances in end-to-end automatic speech recognition. APSIPA Trans. Signal Inf. Process. 11(1) (2022)","DOI":"10.1561\/116.00000050"},{"key":"21_CR19","unstructured":"MetaVoice: Metavoice (2024). https:\/\/github.com\/metavoiceio\/metavoice-src. Accessed 16 Feb 2024"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Mhlanga, D.: Open AI in education, the responsible and ethical use of ChatGPT towards lifelong learning. Education, the Responsible and Ethical Use of ChatGPT Towards Lifelong Learning, 11 February 2023","DOI":"10.2139\/ssrn.4354422"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"M\u00fcller, N.M., Czempin, P., Dieckmann, F., Froghyar, A., B\u00f6ttinger, K.: Does audio deepfake detection generalize? arXiv preprint arXiv:2203.16263 (2022)","DOI":"10.21437\/Interspeech.2022-108"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Muppalla, S., Jia, S., Lyu, S.: Integrating audio-visual features for multimodal deepfake detection. arXiv preprint arXiv:2310.03827 (2023)","DOI":"10.1109\/URTC60662.2023.10534969"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Neekhara, P., Dolhansky, B., Bitton, J., Ferrer, C.C.: Adversarial threats to deepfake detection: a practical perspective. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 923\u2013932 (2021)","DOI":"10.1109\/CVPRW53098.2021.00103"},{"key":"21_CR24","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Pepino, L., Riera, P., Ferrer, L.: Emotion recognition from speech using wav2vec 2.0 embeddings. arXiv preprint arXiv:2104.03502 (2021)","DOI":"10.21437\/Interspeech.2021-703"},{"key":"21_CR26","unstructured":"Ping, W., et al.: Deep voice 3: scaling text-to-speech with convolutional sequence learning. arXiv preprint arXiv:1710.07654 (2017)"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Qiu, F., et al.: Learning transferable compound expressions from masked autoencoder pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4733\u20134741 (2024)","DOI":"10.1109\/CVPRW63382.2024.00476"},{"key":"21_CR28","unstructured":"Schr\u00f6ter, H., Rosenkranz, T., Maier, A., et\u00a0al.: DeepFilterNet: perceptually motivated real-time speech enhancement. arXiv preprint arXiv:2305.08227 (2023)"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations. arXiv preprint arXiv:1803.02155 (2018)","DOI":"10.18653\/v1\/N18-2074"},{"key":"21_CR30","unstructured":"Shen, X., Yuan, S., Sheng, H., Du, H., Yu, X.: Auslan-Daily: Australian sign language translation for daily communication and news. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Tan, X., et\u00a0al.: NaturalSpeech: end-to-end text-to-speech synthesis with human-level quality. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3356232"},{"key":"21_CR32","unstructured":"Tan, X., Qin, T., Soong, F., Liu, T.Y.: A survey on neural speech synthesis. arXiv preprint arXiv:2106.15561 (2021)"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Taylor, P.: Text-to-Speech Synthesis. Cambridge University Press, Cambridge (2009)","DOI":"10.1017\/CBO9780511816338"},{"key":"21_CR34","unstructured":"Van Den\u00a0Oord, A., et\u00a0al.: WaveNet: a generative model for raw audio. arXiv preprint arXiv:1609.03499, 12 (2016)"},{"key":"21_CR35","unstructured":"Wang, C., et\u00a0al.: Neural codec language models are zero-shot text to speech synthesizers. arXiv preprint arXiv:2301.02111 (2023)"},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Wang, T., et al.: Prosody and voice factorization for few-shot speaker adaptation in the challenge M2voc 2021. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8603\u20138607. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9414427"},{"key":"21_CR37","doi-asserted-by":"publisher","first-page":"101114","DOI":"10.1016\/j.csl.2020.101114","volume":"64","author":"X Wang","year":"2020","unstructured":"Wang, X., et al.: ASVspoof 2019: a large-scale public database of synthesized, converted and replayed speech. Comput. Speech Lang. 64, 101114 (2020)","journal-title":"Comput. Speech Lang."},{"key":"21_CR38","doi-asserted-by":"publisher","first-page":"126523","DOI":"10.1016\/j.neucom.2023.126523","volume":"552","author":"Y Wei","year":"2023","unstructured":"Wei, Y., et al.: MPP-Net: multi-perspective perception network for dense video captioning. Neurocomputing 552, 126523 (2023)","journal-title":"Neurocomputing"},{"issue":"11","key":"21_CR39","doi-asserted-by":"publisher","first-page":"39","DOI":"10.22215\/timreview\/1282","volume":"9","author":"M Westerlund","year":"2019","unstructured":"Westerlund, M.: The emergence of deepfake technology: a review. Technol. Innov. Manage. Rev. 9(11), 39\u201352 (2019)","journal-title":"Technol. Innov. Manage. Rev."},{"key":"21_CR40","unstructured":"Yi, C., Wang, J., Cheng, N., Zhou, S., Xu, B.: Applying wav2vec2.0 to speech recognition in various low-resource languages. arXiv preprint arXiv:2012.12121 (2020)"},{"key":"21_CR41","doi-asserted-by":"crossref","unstructured":"Yi, J., et\u00a0al.: ADD 2022: the first audio deep synthesis detection challenge. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 9216\u20139220. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9746939"},{"key":"21_CR42","doi-asserted-by":"publisher","unstructured":"Yu, D., Deng, L.: Automatic Speech Recognition, vol.\u00a01. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-1-4615-3650-5","DOI":"10.1007\/978-1-4615-3650-5"},{"issue":"6","key":"21_CR43","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1049\/bme2.12031","volume":"10","author":"P Yu","year":"2021","unstructured":"Yu, P., Xia, Z., Fei, J., Lu, Y.: A survey on deepfake video detection. IET Biometrics 10(6), 607\u2013624 (2021)","journal-title":"IET Biometrics"},{"key":"21_CR44","unstructured":"Zhang, W., et al.: Affective behaviour analysis via integrating multi-modal knowledge. arXiv preprint arXiv:2403.10825 (2024)"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-1548-3_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,16]],"date-time":"2025-02-16T09:15:17Z","timestamp":1739697317000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-1548-3_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819615476","9789819615483"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-1548-3_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"17 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macau","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ica3pp2024.scimeeting.cn\/en\/web\/index\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}