{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T06:15:39Z","timestamp":1783923339241,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234370","type":"print"},{"value":"9789819234387","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3438-7_30","type":"book-chapter","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T05:46:25Z","timestamp":1783921585000},"page":"358-370","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FePS-Net: A Frequency Enhanced Prosody\u2013Style Fusion Network for Deepfake Speech Detection"],"prefix":"10.1007","author":[{"given":"Yankai","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guirong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"30_CR1","volume-title":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","author":"B Nguyen","year":"2025","unstructured":"Nguyen, B., et al.: What you read isn\u2019t what you hear: linguistic sensitivity in deep-fake speech detection. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (2025)"},{"key":"30_CR2","doi-asserted-by":"crossref","unstructured":"Zhang, K., Hua, Z., Liu, R., Zhang, Y., Guo, Y.: Phoneme-level feature discrepancies: a key to detecting sophisticated speech deepfakes. Proceedings of the AAAI Conference on Artificial Intelligence. 1066\u20131074. Philadelphia, PA, USA (2025)","DOI":"10.1609\/aaai.v39i1.32093"},{"key":"30_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106320","volume":"175","author":"C Fan","year":"2024","unstructured":"Fan, C., et al.: Spatial reconstructed local attention Res2Net with F0 subband for fake speech detection. Neural Netw. 175, 106320 (2024)","journal-title":"Neural Netw."},{"key":"30_CR4","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.21437\/Interspeech.2022-143","volume-title":"Proceedings of Interspeech 2022","author":"A Babu","year":"2022","unstructured":"Babu, A., Wang, C., Tjandra, A., et al.: XLS-R: self-supervised cross-lingual speech representation learning at scale. In: Proceedings of Interspeech 2022, pp. 2278\u20132282 (2022). https:\/\/doi.org\/10.21437\/Interspeech.2022-143"},{"key":"30_CR5","doi-asserted-by":"publisher","first-page":"1120","DOI":"10.21437\/Interspeech.2024-2156","volume-title":"Proceedings of Interspeech 2024","author":"M Li","year":"2024","unstructured":"Li, M., Zhang, X.P.: Interpretable temporal class activation representation for audio spoofing detection. In: Proceedings of Interspeech 2024, pp. 1120\u20131124 (2024). https:\/\/doi.org\/10.21437\/Interspeech.2024-2156"},{"key":"30_CR6","doi-asserted-by":"publisher","first-page":"67901","DOI":"10.52202\/079017-2168","volume":"37","author":"Y Zhu","year":"2024","unstructured":"Zhu, Y., Koppisetti, S., Tran, T., et al.: SLIM: style-linguistics mismatch model for generalized audio deepfake detection. Adv. Neural Inf. Proces. Syst. 37, 67901\u201367928 (2024)","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"30_CR7","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1145\/3552466.3556526","volume-title":"Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia","author":"J Xue","year":"2022","unstructured":"Xue, J., Fan, C., Lv, Z., et al.: Audio deepfake detection based on a combination of F0 information and real plus imaginary spectrogram features. In: Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia, pp. 19\u201326 (2022)"},{"key":"30_CR8","volume-title":"Proceedings of Interspeech 2025","author":"K Warren","year":"2025","unstructured":"Warren, K., Olszewski, D., Layton, S., et al.: Pitch imperfect: detecting audio deepfakes through acoustic prosodic analysis. In: Proceedings of Interspeech 2025 (2025)"},{"issue":"7","key":"30_CR9","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.1587\/transinf.2015EDP7457","volume":"99","author":"M Morise","year":"2016","unstructured":"Morise, M., Yokomori, F., Ozawa, K.: WORLD: a vocoder-based high-quality speech synthesis system for real-time applications. IEICE Trans. Inf. Syst. 99(7), 1877\u20131884 (2016)","journal-title":"IEICE Trans. Inf. Syst."},{"key":"30_CR10","doi-asserted-by":"publisher","first-page":"1008","DOI":"10.21437\/Interspeech.2019-2249","volume-title":"Proceedings of Interspeech 2019","author":"M Todisco","year":"2019","unstructured":"Todisco, M., Wang, X., Vestman, V., et al.: ASVspoof 2019: future horizons in spoofed and fake audio detection. In: Proceedings of Interspeech 2019, pp. 1008\u20131012 (2019). https:\/\/doi.org\/10.21437\/Interspeech.2019-2249"},{"key":"30_CR11","doi-asserted-by":"publisher","first-page":"2507","DOI":"10.1109\/TASLP.2023.3285283","volume":"31","author":"X Liu","year":"2023","unstructured":"Liu, X., Wang, X., Sahidullah, M., et al.: ASVspoof 2021: towards spoofed and deepfake speech detection in the wild. IEEE\/ACM Trans. Audio Speech Lang. Process. 31, 2507\u20132522 (2023)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"30_CR12","unstructured":"Br\u00fcmmer, N., de Villiers, E.: The BOSARIS toolkit: theory, algorithms and code for surviving the new DCF. arXiv Preprint arXiv:1304.2865. (2013)"},{"key":"30_CR13","doi-asserted-by":"publisher","first-page":"5281","DOI":"10.21437\/Interspeech.2023-1820","volume-title":"Proceedings of Interspeech 2023","author":"E Rosello","year":"2023","unstructured":"Rosello, E., Alan\u00eds, A.G., Gomez, A.M., et al.: A conformer-based classifier for variable-length utterance processing in anti-spoofing. In: Proceedings of Interspeech 2023, pp. 5281\u20135285 (2023)"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Truong, D.T., Tao, R., Nguyen, T., et al.: Temporal-channel modeling in multi-head self-attention for synthetic speech detection. arXiv Preprint arXiv:2406.17376. (2024)","DOI":"10.21437\/Interspeech.2024-659"},{"key":"30_CR15","doi-asserted-by":"publisher","first-page":"6765","DOI":"10.1145\/3664647.3681345","volume-title":"Proceedings of the 32nd ACM International Conference on Multimedia","author":"Q Zhang","year":"2024","unstructured":"Zhang, Q., Wen, S., Hu, T.: Audio deepfake detection with self-supervised XLS-R and SLS classifier. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 6765\u20136773 (2024)"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Xuan, X., Zhu, Z., Zhang, W., et al.: Fake-mamba: real-time speech deepfake detection using bidirectional mamba as self-attention\u2019s alternative. arXiv Preprint arXiv:2508.09294. (2025)","DOI":"10.1109\/ASRU65441.2025.11434679"},{"key":"30_CR17","first-page":"1","volume-title":"ICASSP 2025--2025 IEEE International Conference on Acoustics, Speech and Signal Processing","author":"W Huang","year":"2025","unstructured":"Huang, W., Gu, Y., Wang, Z., et al.: Generalizable audio deepfake detection via latent space refinement and augmentation. In: ICASSP 2025--2025 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1\u20135. IEEE (2025)"},{"key":"30_CR18","doi-asserted-by":"publisher","first-page":"12005","DOI":"10.1109\/TIFS.2025.3626963","volume":"20","author":"T Liu","year":"2025","unstructured":"Liu, T., Truong, D.T., Das, R.K., et al.: Nes2Net: a lightweight nested architecture for foundation model driven speech anti-spoofing. IEEE Trans. Inf. Forensics Secur. 20, 12005\u201312018 (2025)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"Phuong, T.D., Hoang, L.V., Tran, H.D.: Pushing the performance of synthetic speech detection with kolmogorov-arnold networks and self-supervised learning models. arXiv Preprint arXiv:2506.14153. (2025)","DOI":"10.21437\/Interspeech.2025-1411"},{"key":"30_CR20","first-page":"1406","volume-title":"ICASSP 2024--2024 IEEE International Conference on Acoustics, Speech and Signal Processing","author":"C Wang","year":"2024","unstructured":"Wang, C., He, J., Yi, J., et al.: Multi-scale permutation entropy for audio deepfake detection. In: ICASSP 2024--2024 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1406\u20131410. IEEE (2024)"},{"key":"30_CR21","first-page":"1","volume-title":"ICASSP 2025--2025 IEEE International Conference on Acoustics, Speech and Signal Processing","author":"Z Wang","year":"2025","unstructured":"Wang, Z., Fu, R., Wen, Z., et al.: Mixture of experts fusion for fake audio detection using frozen wav2vec 2.0. In: ICASSP 2025--2025 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1\u20135. IEEE (2025)"},{"key":"30_CR22","doi-asserted-by":"publisher","first-page":"1276","DOI":"10.1109\/LSP.2025.3547861","volume":"32","author":"Y Xiao","year":"2025","unstructured":"Xiao, Y., Das, R.K.: XLSR-mamba: a dual-column bidirectional state space model for spoofing attack detection. IEEE Signal Process Lett. 32, 1276\u20131280 (2025)","journal-title":"IEEE Signal Process Lett."},{"key":"30_CR23","first-page":"1","volume-title":"ICASSP 2025--2025 IEEE International Conference on Acoustics, Speech and Signal Processing","author":"Z Jin","year":"2025","unstructured":"Jin, Z., Lang, L., Leng, B.: Wave-spectrogram cross-modal aggregation for audio deepfake detection. In: ICASSP 2025--2025 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1\u20135. IEEE (2025)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3438-7_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T05:46:27Z","timestamp":1783921587000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3438-7_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"ISBN":["9789819234370","9789819234387"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3438-7_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,14]]},"assertion":[{"value":"14 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","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":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}