{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T12:09:06Z","timestamp":1787314146034,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032212993","type":"print"},{"value":"9783032213006","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-21300-6_32","type":"book-chapter","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T13:02:23Z","timestamp":1774357343000},"page":"418-426","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Text Vs. Speech? Detecting Audio Deepfakes on\u00a0Instagram"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1731-7925","authenticated-orcid":false,"given":"Karla","family":"Sch\u00e4fer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,25]]},"reference":[{"key":"32_CR1","doi-asserted-by":"crossref","unstructured":"Alonso-Jim\u00e9nez, P., Bogdanov, D., Pons, J., Serra, X.: Tensorflow audio models in Essentia. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2020)","DOI":"10.1109\/ICASSP40776.2020.9054688"},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Batra, A., Khemani, J., Gumber, A., Kumar, A., Jain, A., Gupta, S.: Socialdf: benchmark dataset and detection model for mitigating harmful deepfake content on social media platforms. In: Proceedings of the 4th ACM International Workshop on Multimedia AI against Disinformation, pp. 81\u201389 (2025)","DOI":"10.1145\/3733567.3735573"},{"key":"32_CR3","doi-asserted-by":"publisher","unstructured":"Conti, E., et al.: Deepfake speech detection through emotion recognition: a semantic approach. In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8962\u20138966 (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9747186","DOI":"10.1109\/ICASSP43922.2022.9747186"},{"key":"32_CR4","doi-asserted-by":"publisher","unstructured":"Doan, T.P., Nguyen-Vu, L., Jung, S., Hong, K.: BTS-e: audio deepfake detection using breathing-talking-silence encoder. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135 (2023). https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10095927","DOI":"10.1109\/ICASSP49357.2023.10095927"},{"key":"32_CR5","unstructured":"Frank, J., Sch\u00f6nherr, L.: WaveFake: a data set to facilitate audio deepfake detection. In: Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2021)"},{"key":"32_CR6","unstructured":"Grootendorst, M.: Bertopic: neural topic modeling with a class-based TF-IDF procedure. arXiv preprint arXiv:2203.05794 (2022)"},{"key":"32_CR7","unstructured":"Hartmann, J.: Emotion english distilroberta-base (2022). https:\/\/huggingface.co\/j-hartmann\/emotion-english-distilroberta-base\/"},{"key":"32_CR8","doi-asserted-by":"publisher","unstructured":"Hennequin, R., Khlif, A., Voituret, F., Moussallam, M.: Spleeter: a fast and efficient music source separation tool with pre-trained models. J. Open Source Softw. 5(50), 2154 (2020).https:\/\/doi.org\/10.21105\/joss.02154, deezer Research","DOI":"10.21105\/joss.02154"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Jung, J.w., et al.: Aasist: audio anti-spoofing using integrated spectro-temporal graph attention networks. In: ICASSP 2022-2022 IEEE International Conference On Acoustics, Speech And Signal Processing (ICASSP), pp. 6367\u20136371. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"M\u00fcller, N.M., Czempin, P., Dieckmann, F., Froghyar, A., B\u00f6ttinger, K.: Does audio deepfake detection generalize? Interspeech (2022)","DOI":"10.21437\/Interspeech.2022-108"},{"issue":"2","key":"32_CR11","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1109\/TBIOM.2021.3059479","volume":"3","author":"A Nautsch","year":"2021","unstructured":"Nautsch, A., et al.: Asvspoof 2019: spoofing countermeasures for the detection of synthesized, converted and replayed speech. IEEE Trans. Biometrics, Behav. Identity Sci. 3(2), 252\u2013265 (2021)","journal-title":"IEEE Trans. Biometrics, Behav. Identity Sci."},{"key":"32_CR12","doi-asserted-by":"publisher","unstructured":"Pianese, A., Cozzolino, D., Poggi, G., Verdoliva, L.: Training-free deepfake voice recognition by leveraging large-scale pre-trained models. In: Proceedings of the 2024 ACM Workshop on Information Hiding and Multimedia Security, pp. 289\u2013294. IH&MMSec \u201924, Association for Computing Machinery, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3658664.3659662","DOI":"10.1145\/3658664.3659662"},{"key":"32_CR13","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: International Conference On Machine Learning, pp. 28492\u201328518. PMLR (2023)"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Sch\u00e4fer, K., Choi, J.E., Steinebach, M.: Audio deepfake detection under post-processing attack. In: European Signal Processing Conference 2025 (2025)","DOI":"10.23919\/EUSIPCO63237.2025.11226066"},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"Sivaraman, G., Tak, H., Khoury, E.: Investigating voiced and unvoiced regions of speech for audio deepfake detection. In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2025)","DOI":"10.1109\/ICASSP49660.2025.10890861"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Tak, H., Todisco, M., Wang, X., Jung, J.w., Yamagishi, J., Evans, N.: Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation. In: The Speaker and Language Recognition Workshop (2022)","DOI":"10.21437\/Odyssey.2022-16"},{"key":"32_CR17","doi-asserted-by":"crossref","unstructured":"Wang, X., et\u00a0al.: Asvspoof 5: crowdsourced speech data, deepfakes, and adversarial attacks at scale. arXiv preprint arXiv:2408.08739 (2024)","DOI":"10.21437\/ASVspoof.2024-1"},{"key":"32_CR18","doi-asserted-by":"crossref","unstructured":"Wang, X., Yamagishi, J.: Can large-scale vocoded spoofed data improve speech spoofing countermeasure with a self-supervised front end? In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 10311\u201310315. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10446331"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-21300-6_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T13:02:33Z","timestamp":1774357353000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-21300-6_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032212993","9783032213006"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-21300-6_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"25 March 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The author has no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Delft","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 March 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 April 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"48","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecir2026.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}