{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:43:49Z","timestamp":1753602229232,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031746260"},{"type":"electronic","value":"9783031746277"}],"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\/978-3-031-74627-7_39","type":"book-chapter","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T14:01:15Z","timestamp":1735653675000},"page":"469-479","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["All-for-One and\u00a0One-for-All: Deep Learning-Based Feature Fusion for\u00a0Synthetic Speech Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0727-3725","authenticated-orcid":false,"given":"Daniele","family":"Mari","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5163-3364","authenticated-orcid":false,"given":"Davide","family":"Salvi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0406-0222","authenticated-orcid":false,"given":"Paolo","family":"Bestagini","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8266-5839","authenticated-orcid":false,"given":"Simone","family":"Milani","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,1,1]]},"reference":[{"key":"39_CR1","unstructured":"AlBadawy, E.A., Lyu, S., Farid, H.: Detecting AI-synthesized speech using bispectral analysis. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)"},{"key":"39_CR2","doi-asserted-by":"crossref","unstructured":"Alzantot, M., Wang, Z., Srivastava, M.B.: Deep residual neural networks for audio spoofing detection. In: Conference of the International Speech Communication Association (INTERSPEECH) (2019)","DOI":"10.21437\/Interspeech.2019-3174"},{"key":"39_CR3","unstructured":"Ars Technica: Deepfake Bruce Willis may be the next Hollywood star, and he\u2019s OK with that (2022). https:\/\/arstechnica.com\/information-technology\/2022\/09\/bruce-willis-sells-deepfake-rights-to-his-likeness-for-commercial-use\/"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Attorresi, L., Salvi, D., Borrelli, C., Bestagini, P., Tubaro, S.: Combining automatic speaker verification and prosody analysis for synthetic speech detection. In: International Conference on Pattern Recognition (2022)","DOI":"10.1007\/978-3-031-37742-6_21"},{"key":"39_CR5","unstructured":"BBC News: False claims of deepfake President Biden go viral (2022). https:\/\/www.bbc.com\/news\/62338593"},{"issue":"1","key":"39_CR6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13635-020-00115-w","volume":"2021","author":"C Borrelli","year":"2021","unstructured":"Borrelli, C., Bestagini, P., Antonacci, F., Sarti, A., Tubaro, S.: Synthetic speech detection through short-term and long-term prediction traces. EURASIP J. Inf. Secur. 2021(1), 1\u201314 (2021)","journal-title":"EURASIP J. Inf. Secur."},{"key":"39_CR7","doi-asserted-by":"crossref","unstructured":"Conti, E., Salvi, D., Borrelli, C., et al.: Deepfake speech detection through emotion recognition: a semantic approach. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2022)","DOI":"10.1109\/ICASSP43922.2022.9747186"},{"key":"39_CR8","unstructured":"Jordal, I.: Audiomentations. https:\/\/github.com\/iver56\/audiomentations (2022)"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Kaneko, T., Kameoka, H., Tanaka, K., Hojo, N.: CycleGAN-VC2: improved CycleGAN-based non-parallel voice conversion. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2019)","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"39_CR10","unstructured":"Ito, K., Johnson, L.: The LJSpeech dataset (2017). https:\/\/keithito.com\/LJ-Speech-Dataset\/"},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Lieto, A., Moro, D., Devoti, F., et\u00a0al.: Hello? Who am I lto? a shallow CNN approach for human vs. bot speech classification. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2019)","DOI":"10.1109\/ICASSP.2019.8682743"},{"key":"39_CR12","doi-asserted-by":"crossref","unstructured":"Mari, D., Latora, F., Milani, S.: The sound of silence: efficiency of first digit features in synthetic audio detection. In: IEEE International Workshop on Information Forensics and Security (WIFS) (2022)","DOI":"10.1109\/WIFS55849.2022.9975404"},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Monteiro, J., Alam, J., Falk, T.H.: Generalized end-to-end detection of spoofing attacks to automatic speaker recognizers. Comput. Speech Lang. (2020)","DOI":"10.1016\/j.csl.2020.101096"},{"key":"39_CR14","doi-asserted-by":"publisher","first-page":"103525","DOI":"10.1016\/j.cviu.2022.103525","volume":"223","author":"TT Nguyen","year":"2022","unstructured":"Nguyen, T.T., Nguyen, Q.V.H., et al.: Deep learning for deepfakes creation and detection: a survey. Comput. Vis. Image Underst. 223, 103525 (2022)","journal-title":"Comput. Vis. Image Underst."},{"key":"39_CR15","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: LIBRISPEECH: an ASR corpus based on public domain audio books. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"39_CR16","unstructured":"Ren, Y., et al.: FastSpeech: fast, robust and controllable text to speech. In: Advances in Neural Information Processing Systems (NEURIPS) (2019)"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Salvi, D., et al.: A robust approach to multimodal deepfake detection. J. Imag. (2022)","DOI":"10.3390\/jimaging9060122"},{"key":"39_CR18","doi-asserted-by":"crossref","unstructured":"Sanderson, C., Lovell, B.C.: Multi-region probabilistic histograms for robust and scalable identity inference. In: International Conference on Biometrics (2009)","DOI":"10.1007\/978-3-642-01793-3_21"},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"Tanaka, K., Kameoka, H., et al.: AttS2S-VC: sequence-to-sequence voice conversion with attention and context preservation mechanisms. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2019)","DOI":"10.1109\/ICASSP.2019.8683282"},{"key":"39_CR20","doi-asserted-by":"crossref","unstructured":"Todisco, M., Wang, X., Vestman, V., et\u00a0al.: ASVspoof 2019: future horizons in spoofed and fake audio detection. In: Conference of the International Speech Communication Association (INTERSPEECH) (2019)","DOI":"10.21437\/Interspeech.2019-2249"},{"issue":"5","key":"39_CR21","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1109\/JSTSP.2020.3002101","volume":"14","author":"L Verdoliva","year":"2020","unstructured":"Verdoliva, L.: Media forensics and deepfakes: an overview. IEEE J. Sel. Top. Sig. Process. 14(5), 910\u2013932 (2020)","journal-title":"IEEE J. Sel. Top. Sig. Process."},{"key":"39_CR22","doi-asserted-by":"crossref","unstructured":"Wang, Y., et\u00a0al.: Tacotron: towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135 (2017)","DOI":"10.21437\/Interspeech.2017-1452"},{"issue":"4","key":"39_CR23","doi-asserted-by":"publisher","first-page":"684","DOI":"10.1109\/JSTSP.2016.2647199","volume":"11","author":"C Zhang","year":"2017","unstructured":"Zhang, C., Yu, C., Hansen, J.H.: An investigation of deep-learning frameworks for speaker verification antispoofing. IEEE J. Sel. Top. Sig. Process. 11(4), 684\u2013694 (2017)","journal-title":"IEEE J. Sel. Top. Sig. Process."}],"container-title":["Communications in Computer and Information Science","Machine Learning and Principles and Practice of Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-74627-7_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T14:16:16Z","timestamp":1735654576000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-74627-7_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031746260","9783031746277"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-74627-7_39","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"1 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}