{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T15:13:28Z","timestamp":1783523608581,"version":"3.55.0"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032308481","type":"print"},{"value":"9783032308498","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\/978-3-032-30849-8_10","type":"book-chapter","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T14:15:01Z","timestamp":1783520101000},"page":"172-191","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Human-Centered Explanations for Audio Deepfakes: Making Machine Reasoning Human-Perceptible Through Voice Traits"],"prefix":"10.1007","author":[{"given":"Md","family":"Shajalal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md Mahedi Hasan","family":"Riday","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sima","family":"Amirkhani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gunnar","family":"Stevens","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,9]]},"reference":[{"issue":"1","key":"10_CR1","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/s42001-024-00250-1","volume":"7","author":"E Ferrara","year":"2024","unstructured":"Ferrara, E.: Genai against humanity: nefarious applications of generative artificial intelligence and large language models. J. Comput. Social Sci. 7(1), 549\u2013569 (2024)","journal-title":"J. Comput. Social Sci."},{"key":"10_CR2","unstructured":"Bateman, J.: Deepfakes and synthetic media in the financial system: Assessing threat scenarios. Carnegie Endowment for International Peace (2022)"},{"key":"10_CR3","unstructured":"Yi, J., Wang, C., Tao, J., Zhang, X., Zhang, C.Y., Zhao, Y.: Audio deepfake detection: a survey. arXiv preprint arXiv:2308.14970 (2023)"},{"issue":"8","key":"10_CR4","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.13322","volume":"40","author":"A Dixit","year":"2023","unstructured":"Dixit, A., Kaur, N., Kingra, S.: Review of audio deepfake detection techniques: issues and prospects. Expert. Syst. 40(8), e13322 (2023)","journal-title":"Expert. Syst."},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Nicolas, M., M\u00fcller, P., Czempin, F., Dieckmann, A., Froghyar, K.: B\u00f6ttinger: Does audio deepfake detection generalize?. arXiv preprint arXiv:2203.16263 (2022)","DOI":"10.21437\/Interspeech.2022-108"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Chen, T., Kumar, A., Nagarsheth, P., Sivaraman, G., Khoury, E.: Generalization of audio deepfake detection. In: Odyssey, pp. 132\u2013137 (2020)","DOI":"10.21437\/Odyssey.2020-19"},{"key":"10_CR7","unstructured":"Frank, J., Sch\u00f6nherr, L.: Wavefake: a data set to facilitate audio deepfake detection. arXiv preprint arXiv:2111.02813 (2021)"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Lim, S.N.: Joint audio-visual deepfake detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14800\u201314809 (2021)","DOI":"10.1109\/ICCV48922.2021.01453"},{"key":"10_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.104145","volume":"249","author":"C Bisogni","year":"2024","unstructured":"Bisogni, C., Loia, V., Nappi, M., Pero, C.: Acoustic features analysis for explainable machine learning-based audio spoofing detection. Comput. Vis. Image Underst. 249, 104145 (2024)","journal-title":"Comput. Vis. Image Underst."},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Govindu, A., Kale, P., Hullur, A., Gurav, A., Godse, P.: Deepfake audio detection and justification with explainable artificial intelligence (xai), (2023)","DOI":"10.21203\/rs.3.rs-3444277\/v1"},{"key":"10_CR11","unstructured":"Xie, Z., et al.: Fakesound2: a benchmark for explainable and generalizable deepfake sound detection. arXiv preprint arXiv:2509.17162 (2025)"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Rahman, T., Chakma, R., Mahmud, T.: Beyond accuracy: explainable multimodal deepfake detection through cross-modal feature analysis and dynamic attention weighting. In: 2025 International Conference on Quantum Photonics, Artificial Intelligence, and Networking (QPAIN), pp. 1\u20136. IEEE (2025)","DOI":"10.1109\/QPAIN66474.2025.11171737"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Ijaz Ul Haq, K.M., Malik, K.: Muhammad: multimodal neurosymbolic approach for explainable deepfake detection. ACM Trans. Multimedia Comput. Commun. Appl. 20(11) (2024)","DOI":"10.1145\/3624748"},{"key":"10_CR14","unstructured":"Amirkhani, S., Stevens, G., Shajalal, Md., Boden, A.: The sound of synthetic: a scoping review of human perception in detecting synthetic voices. In: Mensch und Computer 2025-Workshopband, pp. 10\u201318420 (2025)"},{"key":"10_CR15","unstructured":"Amirkhani, S., Stevens, G., Shajalal, M.D., Boden, A.: Detecting the undetectable: Human judgments and the challenge of synthetic voices. In: Proceedings of the 12th International Conference on Communities & Technologies (C&T 2025). European Society for Socially Embedded Technologies (EUSSET) (2025)"},{"issue":"1\u20132","key":"10_CR16","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/S0167-6393(02)00084-5","volume":"40","author":"KR Scherer","year":"2003","unstructured":"Scherer, K.R.: Vocal communication of emotion: a review of research paradigms. Speech Commun. 40(1\u20132), 227\u2013256 (2003)","journal-title":"Speech Commun."},{"key":"10_CR17","unstructured":"Ladgfoged, P.: A course in phonetics. Heinle & Heinle (2001)"},{"issue":"1","key":"10_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1558\/ijsll.38028","volume":"26","author":"E Gold","year":"2019","unstructured":"Gold, E., French, P.: International practices in forensic speaker comparisons. Int. J. Speech Lang. Law 26(1), 1\u201320 (2019)","journal-title":"Int. J. Speech Lang. Law"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Yang, T., Sun, C., Lyu, S., Rose, P.: Forensic deepfake audio detection using segmental speech features. arXiv preprint arXiv:2505.13847 (2025)","DOI":"10.1016\/j.forsciint.2025.112768"},{"key":"10_CR20","unstructured":"Ahmadiadli, Y., Zhang, X.-P., Khan, N.: Beyond identity: a generalizable approach for deepfake audio detection. arXiv preprint arXiv:2505.06766 (2025)"},{"key":"10_CR21","unstructured":"Warren, K., Olszewski, D., Layton, S., Butler, K., Gates, C., Traynor, P.: Pitch imperfect: detecting audio deepfakes through acoustic prosodic analysis. arXiv preprint arXiv:2502.14726 (2025)"},{"key":"10_CR22","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","volume":"58","author":"AB Arrieta","year":"2020","unstructured":"Arrieta, A.B., et al.: Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 58, 82\u2013115 (2020)","journal-title":"Inf. Fusion"},{"key":"10_CR23","unstructured":"Shajalal, Md.: Towards human-centered actionable explainable ai-enabled systems (2025)"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Ehsan, U., Liao, Q.V., Muller, M., Riedl, M.O., Weisz, J.D.: Expanding explainability: towards social transparency in ai systems. In: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, pp. 1\u201319 (2021)","DOI":"10.1145\/3411764.3445188"},{"key":"10_CR25","doi-asserted-by":"publisher","unstructured":"Shajalal, Md., Boden, A., Stevens, G., Du, D., Kern, D.R.: Explaining AI decisions: towards achieving human-centered explainability in smart home environments. In: World Conference on Explainable Artificial Intelligence, pp. 418\u2013440. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-63803-9_23","DOI":"10.1007\/978-3-031-63803-9_23"},{"issue":"3","key":"10_CR26","doi-asserted-by":"publisher","first-page":"3447","DOI":"10.1007\/s13369-021-06297-w","volume":"47","author":"J Khochare","year":"2022","unstructured":"Khochare, J., Joshi, C., Yenarkar, B., Suratkar, S., Kazi, F.: A deep learning framework for audio deepfake detection. Arab. J. Sci. Eng. 47(3), 3447\u20133458 (2022)","journal-title":"Arab. J. Sci. Eng."},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Yan, X., et al.: An initial investigation for detecting vocoder fingerprints of fake audio. In: Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia, pp. 61\u201368 (2022)","DOI":"10.1145\/3552466.3556525"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Qais, A., Rastogi, A., Saxena, A., Rana, A., Sinha, D.: Deepfake audio detection with neural networks using audio features. In: 2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP), pp. 1\u20136. IEEE (2022)","DOI":"10.1109\/ICICCSP53532.2022.9862519"},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Gu, H., et al.: Allm4add: unlocking the capabilities of audio large language models for audio deepfake detection. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 11736\u201311745 (2025)","DOI":"10.1145\/3746027.3755851"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"El Kheir, Y., Samih, Y., Maharjan, S., Polzehl, T., M\u00f6ller, S.: Comprehensive layer-wise analysis of SSL models for audio deepfake detection. In: Findings of the Association for Computational Linguistics: NAACL 2025, pp. 4070\u20134082 (2025)","DOI":"10.18653\/v1\/2025.findings-naacl.227"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Wu, H., et al. Clad: robust audio deepfake detection against manipulation attacks with contrastive learning. Knowl.-Based Syst. 115179 (2025)","DOI":"10.1016\/j.knosys.2025.115179"},{"key":"10_CR32","volume":"81","author":"Yu Ning","year":"2024","unstructured":"Ning, Yu., Chen, L., Leng, T., Chen, Z., Yi, X.: An explainable deepfake of speech detection method with spectrograms and waveforms. J. Inf. Secur. Appl. 81, 103720 (2024)","journal-title":"J. Inf. Secur. Appl."},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Grinberg, P., Kumar, A., Koppisetti, S., Bharaj, G.: What does an audio deepfake detector focus on? A study in the time domain. In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2025)","DOI":"10.1109\/ICASSP49660.2025.10887568"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Grinberg, P., Kumar, A., Koppisetti, S., Bharaj, G.: A data-driven diffusion-based approach for audio deepfake explanations. arXiv preprint arXiv:2506.03425 (2025)","DOI":"10.21437\/Interspeech.2025-2105"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Cuccovillo, L., et al.: Open challenges in synthetic speech detection. In: 2022 IEEE International Workshop on Information Forensics and Security (WIFS), pp. 1\u20136. IEEE (2022)","DOI":"10.1109\/WIFS55849.2022.9975433"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Tariq, S., Woo, S.S., Singh, P., Irmalasari, I., Gupta, S., Gupta, D.: From prediction to explanation: multimodal, explainable, and interactive deepfake detection framework for non-expert users. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 11716\u201311725 (2025)","DOI":"10.1145\/3746027.3755786"},{"key":"10_CR37","unstructured":"Rabiner, L., Juang, B.-H.: Fundamentals of Speech Recognition. Prentice-Hall Inc. (1993)"},{"key":"10_CR38","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1016\/j.csl.2017.01.001","volume":"45","author":"M Todisco","year":"2017","unstructured":"Todisco, M., Delgado, H., Evans, N.: Constant q cepstral coefficients: a spoofing countermeasure for automatic speaker verification. Comput. Speech Lang. 45, 516\u2013535 (2017)","journal-title":"Comput. Speech Lang."},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Dejonckere, P.H., et al.: A basic protocol for functional assessment of voice pathology, especially for investigating the efficacy of (phonosurgical) treatments and evaluating new assessment techniques: guideline elaborated by the committee on phoniatrics of the European laryngological society (els). Eur. Arch. Oto-rhino-laryngology 258(2), 77\u201382 (2001)","DOI":"10.1007\/s004050000299"},{"key":"10_CR40","unstructured":"Baken, R.J., Orlikoff, R.F.: Clinical Measurement of Speech and Voice. Speech Science. Singular Thomson Learning (2000)"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Singh, S., Guestrin, C.: \u201cwhy should i trust you?\" Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135\u20131144 (2016)","DOI":"10.1145\/2939672.2939778"},{"key":"10_CR42","unstructured":"Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"10_CR43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.artint.2018.07.007","volume":"267","author":"T Miller","year":"2019","unstructured":"Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267, 1\u201338 (2019)","journal-title":"Artif. Intell."},{"key":"10_CR44","doi-asserted-by":"publisher","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":"10_CR45","unstructured":"Hoffman, R.R., Mueller, S.T., Klein, G., Litman, J.: Metrics for explainable AI: challenges and prospects. arXiv preprint arXiv:1812.04608 (2018)"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in HCI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-30849-8_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T14:15:09Z","timestamp":1783520109000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-30849-8_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032308481","9783032308498"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-30849-8_10","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":"9 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"HCII","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Human-Computer Interaction","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Montreal, 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":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"hcii2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2026.hci.international\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}