{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T11:05:16Z","timestamp":1784027116152,"version":"3.55.0"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032207319","type":"print"},{"value":"9783032207326","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\/978-3-032-20732-6_24","type":"book-chapter","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T10:28:09Z","timestamp":1784024889000},"page":"376-389","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Lightweight On-Device Audio Deepfake Detection Using Squeezeformers"],"prefix":"10.1007","author":[{"given":"Ashkan","family":"Moradi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiago H.","family":"Falk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,2]]},"reference":[{"key":"24_CR1","doi-asserted-by":"publisher","first-page":"1400024","DOI":"10.3389\/fdata.2024.1400024","volume":"7","author":"E Altuncu","year":"2024","unstructured":"Altuncu, E., Franqueira, V.N., Li, S.: Deepfake: definitions, performance metrics and standards, datasets, and a meta-review. Front. Big Data 7, 1400024 (2024)","journal-title":"Front. Big Data"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Babu, A., et al.: XLS-R: self-supervised cross-lingual speech representation learning at scale (2021). arXiv preprint arXiv:2111.09296","DOI":"10.21437\/Interspeech.2022-143"},{"key":"24_CR3","first-page":"12449","volume":"33","author":"A Baevski","year":"2020","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)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Baldwin, S.: Compute Canada: advancing computational research. In: Journal of Physics: Conference Series. vol.\u00a0341, p. 012001. IOP Publishing (2012)","DOI":"10.1088\/1742-6596\/341\/1\/012001"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Chaiwongyen, A., Duangpummet, S., Karnjana, J., Kongprawechnon, W., Unoki, M.: Potential of speech-pathological features for deepfake speech detection. IEEE Access (2024)","DOI":"10.1109\/ACCESS.2024.3447582"},{"issue":"26","key":"24_CR6","doi-asserted-by":"publisher","first-page":"67443","DOI":"10.1007\/s11042-024-18217-9","volume":"83","author":"N Chakravarty","year":"2024","unstructured":"Chakravarty, N., Dua, M.: A lightweight feature extraction technique for deepfake audio detection. Multimedia Tools Appl. 83(26), 67443\u201367467 (2024)","journal-title":"Multimedia Tools Appl."},{"issue":"6","key":"24_CR7","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","volume":"16","author":"S Chen","year":"2022","unstructured":"Chen, S., et al.: WavLM: large-scale self-supervised pre-training for full stack speech processing. IEEE J. Sel. Top. Sig. Process. 16(6), 1505\u20131518 (2022)","journal-title":"IEEE J. Sel. Top. Sig. Process."},{"key":"24_CR8","doi-asserted-by":"crossref","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. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095927"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Gulati, A., et\u00a0al.: Conformer: convolution-augmented transformer for speech recognition (2020). arXiv preprint arXiv:2005.08100","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Guo, Y., Huang, H., Chen, X., Zhao, H., Wang, Y.: Audio deepfake detection with self-supervised WavLM and multi-fusion attentive classifier. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 12702\u201312706. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10447923"},{"key":"24_CR11","doi-asserted-by":"publisher","first-page":"134018","DOI":"10.1109\/ACCESS.2022.3231480","volume":"10","author":"A Hamza","year":"2022","unstructured":"Hamza, A., et al.: Deepfake audio detection via MFCC features using machine learning. IEEE Access 10, 134018\u2013134028 (2022)","journal-title":"IEEE Access"},{"key":"24_CR12","doi-asserted-by":"publisher","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","volume":"29","author":"WN Hsu","year":"2021","unstructured":"Hsu, W.N., Bolte, B., Tsai, Y.H.H., Lakhotia, K., Salakhutdinov, R., Mohamed, A.: Hubert: self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM transactions on audio, speech, and language processing 29, 3451\u20133460 (2021)","journal-title":"IEEE\/ACM transactions on audio, speech, and language processing"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Jung, J.w., et al.: AASISIT-L: 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":"24_CR14","unstructured":"Khanjani, Z., Watson, G., Janeja, V.P.: How deep are the fakes? focusing on audio deepfake: a survey (2021). arXiv preprint arXiv:2111.14203"},{"key":"24_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":"24_CR16","doi-asserted-by":"crossref","first-page":"9361","DOI":"10.52202\/068431-0680","volume":"35","author":"S Kim","year":"2022","unstructured":"Kim, S., et al.: Squeezeformer: an efficient transformer for automatic speech recognition. Adv. Neural. Inf. Process. Syst. 35, 9361\u20139373 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Ko, T., Peddinti, V., Povey, D., Seltzer, M.L., Khudanpur, S.: A study on data augmentation of reverberant speech for robust speech recognition. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5220\u20135224. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"24_CR18","unstructured":"Latif, S., Zaidi, A., Cuayahuitl, H., Shamshad, F., Shoukat, M., Qadir, J.: Transformers in speech processing: a survey (2023). arXiv preprint arXiv:2303.11607"},{"issue":"7","key":"24_CR19","first-page":"1","volume":"57","author":"M Li","year":"2025","unstructured":"Li, M., Ahmadiadli, Y., Zhang, X.P.: A survey on speech deepfake detection. ACM Comput. Surv. 57(7), 1\u201338 (2025)","journal-title":"ACM Comput. Surv."},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"Liu, K., Wang, Y., Li, S., Shao, X.: Speech formants integration for generalized detection of synthetic speech spoofing attacks. In: Proceeding of INTERSPEECH 2024 (2024)","DOI":"10.21437\/Interspeech.2024-292"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Audio self-supervised learning: a survey. Patterns 3(12) (2022)","DOI":"10.1016\/j.patter.2022.100616"},{"issue":"1","key":"24_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3425780","volume":"54","author":"Y Mirsky","year":"2021","unstructured":"Mirsky, Y., Lee, W.: The creation and detection of deepfakes: a survey. ACM Comput. Surv. (CSUR) 54(1), 1\u201341 (2021)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"24_CR23","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"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Pan, Z., Liu, T., Sailor, H.B., Wang, Q.: Attentive merging of hidden embeddings from pre-trained speech model for anti-spoofing detection (2024). arXiv preprint arXiv:2406.10283","DOI":"10.21437\/Interspeech.2024-1472"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Pan, Z., Zhuang, B., Liu, J., He, H., Cai, J.: Scalable vision transformers with hierarchical pooling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 377\u2013386 (2021)","DOI":"10.1109\/ICCV48922.2021.00043"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Pham, L., Lam, P., Nguyen, T., Nguyen, H., Schindler, A.: Deepfake audio detection using spectrogram-based feature and ensemble of deep learning models. In: 2024 IEEE 5th International Symposium on the Internet of Sounds (IS2), pp.\u00a01\u20135. IEEE (2024)","DOI":"10.1109\/IS262782.2024.10704095"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Pimentel, A., Zhu, Y., Guimar\u00e3es, H.R., Falk, T.H.: Efficient audio deepfake detection using WavLM with early exiting. In: 2024 IEEE International Workshop on Information Forensics and Security (WIFS), pp.\u00a01\u20136. IEEE (2024)","DOI":"10.1109\/WIFS61860.2024.10810699"},{"key":"24_CR28","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":"24_CR29","unstructured":"Rose, R., Cohen, M.: Political consultant behind fake biden AI robocall faces charges in new hampshire (2024). https:\/\/www.cnn.com\/2024\/05\/23\/politics\/new-hampshire-ai-robocall-biden-charges\/index.html. Accessed 30 June 2025"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Shin, H.s., Heo, J., Kim, J.h., Lim, C.y., Kim, W., Yu, H.J.: HM-conformer: a conformer-based audio deepfake detection system with hierarchical pooling and multi-level classification token aggregation methods. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 10581\u201310585. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10448453"},{"key":"24_CR31","unstructured":"Snyder, D., Chen, G., Povey, D.: MUSAN: a music, speech, and noise corpus (2015). arXiv preprint arXiv:1510.08484"},{"key":"24_CR32","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 (2022). arXiv preprint arXiv:2202.12233","DOI":"10.21437\/Odyssey.2022-16"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Todisco, M., et al.: ASVspoof 2019: future horizons in spoofed and fake audio detection (2019). arXiv preprint arXiv:1904.05441","DOI":"10.21437\/Interspeech.2019-2249"},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.: fully automated end-to-end fake audio detection. In: Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia, pp. 27\u201333 (2022)","DOI":"10.1145\/3552466.3556530"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"Wang, X., Yamagishi, J.: A comparative study on recent neural spoofing countermeasures for synthetic speech detection (2021). arXiv preprint arXiv:2103.11326","DOI":"10.21437\/Interspeech.2021-702"},{"key":"24_CR36","doi-asserted-by":"crossref","unstructured":"Yamagishi, J., et\u00a0al.: ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection (2021). arXiv preprint arXiv:2109.00537","DOI":"10.21437\/ASVSPOOF.2021-8"},{"key":"24_CR37","doi-asserted-by":"crossref","unstructured":"Yang, S.w., et\u00a0al.: A large-scale evaluation of speech foundation models. IEEE\/ACM Trans. Audio Speech Lang. Process. 32, pp. 2884\u20132899 (2024)","DOI":"10.1109\/TASLP.2024.3389631"},{"key":"24_CR38","doi-asserted-by":"crossref","unstructured":"Yang, Y., et al.: A robust audio deepfake detection system via multi-view feature. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 13131\u201313135. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10446560"},{"issue":"7","key":"24_CR39","doi-asserted-by":"publisher","first-page":"1989","DOI":"10.3390\/s25071989","volume":"25","author":"B Zhang","year":"2025","unstructured":"Zhang, B., Cui, H., Nguyen, V., Whitty, M.: Audio deepfake detection: what has been achieved and what lies ahead. Sensors (Basel, Switzerland) 25(7), 1989 (2025)","journal-title":"Sensors (Basel, Switzerland)"},{"key":"24_CR40","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1109\/LSP.2021.3076358","volume":"28","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Jiang, F., Duan, Z.: One-class learning towards synthetic voice spoofing detection. IEEE Signal Process. Lett. 28, 937\u2013941 (2021)","journal-title":"IEEE Signal Process. Lett."},{"key":"24_CR41","doi-asserted-by":"crossref","first-page":"67901","DOI":"10.52202\/079017-2168","volume":"37","author":"Y Zhu","year":"2024","unstructured":"Zhu, Y., Koppisetti, S., Tran, T., Bharaj, G.: Slim: style-linguistics mismatch model for generalized audio deepfake detection. Adv. Neural. Inf. Process. Syst. 37, 67901\u201367928 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR42","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Powar, S., Falk, T.H.: Characterizing the temporal dynamics of universal speech representations for generalizable deepfake detection. In: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), pp. 139\u2013143. IEEE (2024)","DOI":"10.1109\/ICASSPW62465.2024.10626010"}],"container-title":["Lecture Notes in Computer Science","Risks and Security of Internet and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-20732-6_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T10:28:14Z","timestamp":1784024894000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-20732-6_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032207319","9783032207326"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-20732-6_24","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":"2 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that\u00a0are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"CRiSIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Risks and Security of Internet and Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Gatineau, QC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"crisis2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/crisis2025.uqo.ca\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}