{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:47:02Z","timestamp":1784180822875,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,14]]},"DOI":"10.1145\/3552466.3556531","type":"proceedings-article","created":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T12:27:26Z","timestamp":1664627246000},"page":"85-91","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":53,"title":["Human Perception of Audio Deepfakes"],"prefix":"10.1145","author":[{"given":"Nicolas M.","family":"M\u00fcller","sequence":"first","affiliation":[{"name":"Fraunhofer AISEC, TU Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karla","family":"Pizzi","sequence":"additional","affiliation":[{"name":"Fraunhofer AISEC, TU Munich, Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jennifer","family":"Williams","sequence":"additional","affiliation":[{"name":"University of Southampton, Southampton, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"October","author":"Adams Matt","year":"2017","unstructured":"Matt Adams . Google Assistant Now Sounds More Realistic Thanks to DeepMind , October 2017 . URL https:\/\/www.androidauthority.com\/google-assistantwavenet-deepmind-805224\/. Matt Adams. Google Assistant Now Sounds More Realistic Thanks to DeepMind, October 2017. URL https:\/\/www.androidauthority.com\/google-assistantwavenet-deepmind-805224\/."},{"key":"e_1_3_2_2_2_1","article-title":"AI Voice Actors Sound More Human Than Ever -- And They're Ready to Hire","author":"Hao Karen","year":"2021","unstructured":"Karen Hao . AI Voice Actors Sound More Human Than Ever -- And They're Ready to Hire . MIT Technology Review Cambridge , July 2021 . URL https:\/\/www. technologyreview.com\/2021\/07\/09\/1028140\/ai-voice-actors-sound-human\/. Karen Hao. AI Voice Actors Sound More Human Than Ever -- And They're Ready to Hire. MIT Technology Review Cambridge, July 2021. URL https:\/\/www. technologyreview.com\/2021\/07\/09\/1028140\/ai-voice-actors-sound-human\/.","journal-title":"MIT Technology Review Cambridge"},{"key":"e_1_3_2_2_3_1","first-page":"1753","article-title":"A Looming Challenge for Privacy, Democracy, and National Security","volume":"107","author":"Chesney Bobby","year":"2019","unstructured":"Bobby Chesney and Danielle Citron . Deep Fakes : A Looming Challenge for Privacy, Democracy, and National Security . California Law Review , 107 : 1753 , 2019 . Bobby Chesney and Danielle Citron. Deep Fakes: A Looming Challenge for Privacy, Democracy, and National Security. California Law Review, 107:1753, 2019.","journal-title":"California Law Review"},{"issue":"11","key":"e_1_3_2_2_4_1","article-title":"The Emergence of Deepfake Technology","volume":"9","author":"Westerlund Mika","year":"2019","unstructured":"Mika Westerlund . The Emergence of Deepfake Technology : A Review. Technology Innovation Management Review , 9 ( 11 ), 2019 . Mika Westerlund. The Emergence of Deepfake Technology: A Review. Technology Innovation Management Review, 9(11), 2019.","journal-title":"A Review. Technology Innovation Management Review"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-9"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"e_1_3_2_2_7_1","volume-title":"The Creation and Detection of Deepfakes: A Survey. ACM Computing Surveys (CSUR), 54(1):1--41","author":"Mirsky Yisroel","year":"2021","unstructured":"Yisroel Mirsky and Wenke Lee . The Creation and Detection of Deepfakes: A Survey. ACM Computing Surveys (CSUR), 54(1):1--41 , 2021 . Yisroel Mirsky and Wenke Lee. The Creation and Detection of Deepfakes: A Survey. ACM Computing Surveys (CSUR), 54(1):1--41, 2021."},{"key":"e_1_3_2_2_8_1","first-page":"1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Rossler Andreas","year":"2019","unstructured":"Andreas Rossler , Davide Cozzolino , Luisa Verdoliva , Christian Riess , Justus Thies , and Matthias Nie\u00dfner . FaceForensics : Learning to Detect Manipulated Facial Images . In Proceedings of the IEEE\/CVF International Conference on Computer Vision , pages 1 -- 11 , 2019 . Andreas Rossler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, and Matthias Nie\u00dfner. FaceForensics: Learning to Detect Manipulated Facial Images. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pages 1--11, 2019."},{"key":"e_1_3_2_2_9_1","volume-title":"Deepfake Detection: Humans vs. Machines. arXiv preprint arXiv:2009.03155v1","author":"Korshunov Pavel","year":"2020","unstructured":"Pavel Korshunov and S\u00e9bastien Marcel . Deepfake Detection: Humans vs. Machines. arXiv preprint arXiv:2009.03155v1 , 2020 . Pavel Korshunov and S\u00e9bastien Marcel. Deepfake Detection: Humans vs. Machines. arXiv preprint arXiv:2009.03155v1, 2020."},{"key":"e_1_3_2_2_10_1","first-page":"2510","volume-title":"Korshunov and S\u00e9bastien Marcel. Subjective and Objective Evaluation of Deepfake Videos. In ICASSP 2021--2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Pavel","year":"2021","unstructured":"Pavel Korshunov and S\u00e9bastien Marcel. Subjective and Objective Evaluation of Deepfake Videos. In ICASSP 2021--2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , pages 2510 -- 2514 , 2021 . Pavel Korshunov and S\u00e9bastien Marcel. Subjective and Objective Evaluation of Deepfake Videos. In ICASSP 2021--2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 2510--2514, 2021."},{"key":"e_1_3_2_2_11_1","volume-title":"Proceedings of the National Academy of Sciences, 119(1)","author":"Groh Matthew","year":"2021","unstructured":"Matthew Groh , Ziv Epstein , Chaz Firestone , and Rosalind Picard . Deepfake Detection by Human Crowds, Machines, and Machine-Informed Crowds . Proceedings of the National Academy of Sciences, 119(1) , Dec 2021 . Matthew Groh, Ziv Epstein, Chaz Firestone, and Rosalind Picard. Deepfake Detection by Human Crowds, Machines, and Machine-Informed Crowds. Proceedings of the National Academy of Sciences, 119(1), Dec 2021."},{"key":"e_1_3_2_2_12_1","first-page":"14","article-title":"Recurrent Convolutional Structures for Audio Spoof and Video Deepfake Detection","author":"Chintha Akash","year":"2020","unstructured":"Akash Chintha , Bao Thai , Saniat Javid Sohrawardi , Kartavya Bhatt , Andrea Hickerson , Matthew Wright , and Raymond Ptucha . Recurrent Convolutional Structures for Audio Spoof and Video Deepfake Detection . IEEE Journal of Selected Topics in Signal Processing , 14 , 2020 . Akash Chintha, Bao Thai, Saniat Javid Sohrawardi, Kartavya Bhatt, Andrea Hickerson, Matthew Wright, and Raymond Ptucha. Recurrent Convolutional Structures for Audio Spoof and Video Deepfake Detection. IEEE Journal of Selected Topics in Signal Processing, 14, 2020.","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"e_1_3_2_2_13_1","first-page":"1078","volume-title":"Mani B Srivastava. Deep Residual Neural Networks for Audio Spoofing Detection. Proceedings of Interspeech 2019","author":"Alzantot Moustafa","year":"2019","unstructured":"Moustafa Alzantot , Ziqi Wang , and Mani B Srivastava. Deep Residual Neural Networks for Audio Spoofing Detection. Proceedings of Interspeech 2019 , pages 1078 -- 1082 , 2019 . Moustafa Alzantot, Ziqi Wang, and Mani B Srivastava. Deep Residual Neural Networks for Audio Spoofing Detection. Proceedings of Interspeech 2019, pages 1078--1082, 2019."},{"key":"e_1_3_2_2_14_1","first-page":"1018","volume-title":"Bob L Sturm. Ensemble Models for Spoofing Detection in Automatic Speaker Verification. Proceedings of Interspeech 2019","author":"Chettri Bhusan","year":"2019","unstructured":"Bhusan Chettri , Daniel Stoller , Veronica Morfi , Marco A Mart\u00ednez Ram\u00edrez , Emmanouil Benetos , and Bob L Sturm. Ensemble Models for Spoofing Detection in Automatic Speaker Verification. Proceedings of Interspeech 2019 , pages 1018 -- 1022 , 2019 . Bhusan Chettri, Daniel Stoller, Veronica Morfi, Marco A Mart\u00ednez Ram\u00edrez, Emmanouil Benetos, and Bob L Sturm. Ensemble Models for Spoofing Detection in Automatic Speaker Verification. Proceedings of Interspeech 2019, pages 1018--1022, 2019."},{"key":"e_1_3_2_2_15_1","first-page":"1352","volume-title":"Zhonghua Li. Densely Connected Convolutional Network for Audio Spoofing Detection. In 2020 AsiaPacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","author":"Wang Zheng","year":"2020","unstructured":"Zheng Wang , Sanshuai Cui , Xiangui Kang , Wei Sun , and Zhonghua Li. Densely Connected Convolutional Network for Audio Spoofing Detection. In 2020 AsiaPacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) , pages 1352 -- 1360 . IEEE, 2020 . Zheng Wang, Sanshuai Cui, Xiangui Kang, Wei Sun, and Zhonghua Li. Densely Connected Convolutional Network for Audio Spoofing Detection. In 2020 AsiaPacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pages 1352--1360. IEEE, 2020."},{"key":"e_1_3_2_2_16_1","volume-title":"Haizhou Li. Detecting Converted Speech and Natural Speech for Anti-Spoofing Attack in Speaker Recognition. In Thirteenth Annual Conference of the International Speech Communication Association","author":"Wu Zhizheng","year":"2012","unstructured":"Zhizheng Wu , Eng Siong Chng , and Haizhou Li. Detecting Converted Speech and Natural Speech for Anti-Spoofing Attack in Speaker Recognition. In Thirteenth Annual Conference of the International Speech Communication Association , 2012 . Zhizheng Wu, Eng Siong Chng, and Haizhou Li. Detecting Converted Speech and Natural Speech for Anti-Spoofing Attack in Speaker Recognition. In Thirteenth Annual Conference of the International Speech Communication Association, 2012."},{"key":"e_1_3_2_2_17_1","first-page":"2087","volume-title":"Cemal Hanil\u00e7i. A Comparison of Features for Synthetic Speech Detection. In Proceedings of Interspeech 2015","author":"Sahidullah Md.","year":"2015","unstructured":"Md. Sahidullah , Tomi Kinnunen , and Cemal Hanil\u00e7i. A Comparison of Features for Synthetic Speech Detection. In Proceedings of Interspeech 2015 , pages 2087 -- 2091 , 2015 . Md. Sahidullah, Tomi Kinnunen, and Cemal Hanil\u00e7i. A Comparison of Features for Synthetic Speech Detection. In Proceedings of Interspeech 2015, pages 2087--2091, 2015."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-1"},{"key":"e_1_3_2_2_19_1","first-page":"222","volume-title":"Odyssey 2020 The Speaker and Language Recognition Workshop","author":"Williams Jennifer","year":"2020","unstructured":"Jennifer Williams , Joanna Rownicka , Pilar Oplustil Gallegos , and Simon King . Comparison of speech representations for automatic quality estimation in multispeaker text-to-speech synthesis . In Odyssey 2020 The Speaker and Language Recognition Workshop , pages 222 -- 229 , 2020 . Jennifer Williams, Joanna Rownicka, Pilar Oplustil Gallegos, and Simon King. Comparison of speech representations for automatic quality estimation in multispeaker text-to-speech synthesis. In Odyssey 2020 The Speaker and Language Recognition Workshop, pages 222--229, 2020."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"e_1_3_2_2_21_1","volume-title":"The VoiceMOS Challenge","author":"Huang Wen-Chin","year":"2022","unstructured":"Wen-Chin Huang , Erica Cooper , Yu Tsao , Hsin-Min Wang , Tomoki Toda , and Junichi Yamagishi . The VoiceMOS Challenge 2022 . arXiv preprint arXiv:2203.11389 2022. Wen-Chin Huang, Erica Cooper, Yu Tsao, Hsin-Min Wang, Tomoki Toda, and Junichi Yamagishi. The VoiceMOS Challenge 2022. arXiv preprint arXiv:2203.11389 2022."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-92627-8_22"},{"key":"e_1_3_2_2_23_1","volume-title":"ASVspoof 2015: the First Automatic Speaker Verification Spoofing and Countermeasures Challenge. Training, 10(15):3750","author":"Wu Zhizheng","year":"2015","unstructured":"Zhizheng Wu , Tomi Kinnunen , Nicholas Evans , Junichi Yamagishi , Cemal Hanil\u00e7i , Md Sahidullah , and Aleksandr Sizov . ASVspoof 2015: the First Automatic Speaker Verification Spoofing and Countermeasures Challenge. Training, 10(15):3750 , 2015 . Zhizheng Wu, Tomi Kinnunen, Nicholas Evans, Junichi Yamagishi, Cemal Hanil\u00e7i, Md Sahidullah, and Aleksandr Sizov. ASVspoof 2015: the First Automatic Speaker Verification Spoofing and Countermeasures Challenge. Training, 10(15):3750, 2015."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.21437\/VCC_BC.2020-15"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"e_1_3_2_2_26_1","volume-title":"Interspeech","author":"Wang Xin","year":"2021","unstructured":"Xin Wang and Junichi Yamagishi . A comparative study on recent neural spoofing countermeasures for synthetic speech detection . In Interspeech , 2021 . Xin Wang and Junichi Yamagishi. A comparative study on recent neural spoofing countermeasures for synthetic speech detection. In Interspeech, 2021."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.21437\/SPSC.2021-11"},{"key":"e_1_3_2_2_28_1","volume-title":"An initial investigation for detecting partially spoofed audio. arXiv preprint arXiv:2104.02518","author":"Zhang Lin","year":"2021","unstructured":"Lin Zhang , Xin Wang , Erica Cooper , Junichi Yamagishi , Jose Patino , and Nicholas Evans . An initial investigation for detecting partially spoofed audio. arXiv preprint arXiv:2104.02518 , 2021 . Lin Zhang, Xin Wang, Erica Cooper, Junichi Yamagishi, Jose Patino, and Nicholas Evans. An initial investigation for detecting partially spoofed audio. arXiv preprint arXiv:2104.02518, 2021."},{"key":"e_1_3_2_2_29_1","volume-title":"The PartialSpoof Database and Countermeasures for the Detection of Short Generated Audio Segments Embedded in a Speech Utterance. arXiv preprint arXiv:2204.05177","author":"Zhang Lin","year":"2022","unstructured":"Lin Zhang , Xin Wang , Erica Cooper , Nicholas Evans , and Junichi Yamagishi . The PartialSpoof Database and Countermeasures for the Detection of Short Generated Audio Segments Embedded in a Speech Utterance. arXiv preprint arXiv:2204.05177 , 2022 . Lin Zhang, Xin Wang, Erica Cooper, Nicholas Evans, and Junichi Yamagishi. The PartialSpoof Database and Countermeasures for the Detection of Short Generated Audio Segments Embedded in a Speech Utterance. arXiv preprint arXiv:2204.05177, 2022."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2016.12.033"},{"key":"e_1_3_2_2_31_1","first-page":"82","volume-title":"Vadim Shchemelinin. Audio Replay Attack Detection with Deep Learning Frameworks. In Proceedings of Interspeech 2017","author":"Lavrentyeva Galina","year":"2017","unstructured":"Galina Lavrentyeva , Sergey Novoselov , Egor Malykh , Alexander Kozlov , Oleg Kudashev , and Vadim Shchemelinin. Audio Replay Attack Detection with Deep Learning Frameworks. In Proceedings of Interspeech 2017 , pages 82 -- 86 , 2017 . Galina Lavrentyeva, Sergey Novoselov, Egor Malykh, Alexander Kozlov, Oleg Kudashev, and Vadim Shchemelinin. Audio Replay Attack Detection with Deep Learning Frameworks. In Proceedings of Interspeech 2017, pages 82--86, 2017."},{"key":"e_1_3_2_2_32_1","first-page":"1033","volume-title":"Novoselov. STC Antispoofing Systems for the ASVspoof2019 Challenge. In Proceedings of Interspeech 2019","author":"Lavrentyeva G","year":"2019","unstructured":"G Lavrentyeva , A Tseren , M Volkova , A Gorlanov , A Kozlov , and S Novoselov. STC Antispoofing Systems for the ASVspoof2019 Challenge. In Proceedings of Interspeech 2019 , pages 1033 -- 1037 , 2019 . G Lavrentyeva, A Tseren, M Volkova, A Gorlanov, A Kozlov, and S Novoselov. STC Antispoofing Systems for the ASVspoof2019 Challenge. In Proceedings of Interspeech 2019, pages 1033--1037, 2019."},{"key":"e_1_3_2_2_33_1","first-page":"4259","volume-title":"Wang and Junichi Yamagishi. A Comparative Study on Recent Neural Spoofing Countermeasures for Synthetic Speech Detection. In Proceedings of Interspeech 2021","author":"Xin","year":"2021","unstructured":"Xin Wang and Junichi Yamagishi. A Comparative Study on Recent Neural Spoofing Countermeasures for Synthetic Speech Detection. In Proceedings of Interspeech 2021 , pages 4259 -- 4263 , 2021 . Xin Wang and Junichi Yamagishi. A Comparative Study on Recent Neural Spoofing Countermeasures for Synthetic Speech Detection. In Proceedings of Interspeech 2021, pages 4259--4263, 2021."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"issue":"4","key":"e_1_3_2_2_36_1","first-page":"1","volume":"2","author":"Felder Richard M","year":"2009","unstructured":"Richard M Felder and Rebecca Brent . Active Learning : An Introduction. ASQ Higher Education Brief , 2 ( 4 ): 1 -- 5 , 2009 . Richard M Felder and Rebecca Brent. Active Learning: An Introduction. ASQ Higher Education Brief, 2(4):1--5, 2009.","journal-title":"An Introduction. ASQ Higher Education Brief"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"e_1_3_2_2_38_1","volume-title":"Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499","author":"van den Oord Aaron","year":"2016","unstructured":"Aaron van den Oord , Sander Dieleman , Heiga Zen , Karen Simonyan , Oriol Vinyals , Alex Graves , Nal Kalchbrenner , Andrew Senior , and Koray Kavukcuoglu . Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499 , 2016 . Aaron van den Oord, Sander Dieleman, Heiga Zen, Karen Simonyan, Oriol Vinyals, Alex Graves, Nal Kalchbrenner, Andrew Senior, and Koray Kavukcuoglu. Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499, 2016."},{"key":"e_1_3_2_2_39_1","volume-title":"High Frequency Hearing Loss","author":"Services Decibel Hearing","year":"2021","unstructured":"Decibel Hearing Services . High Frequency Hearing Loss , 2021 . URL https: \/\/decibelhearing.com\/hearing-loss-overview\/high-frequency-hearing-loss\/. Decibel Hearing Services. High Frequency Hearing Loss, 2021. URL https: \/\/decibelhearing.com\/hearing-loss-overview\/high-frequency-hearing-loss\/."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3552466.3556531","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3552466.3556531","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:25Z","timestamp":1750182565000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3552466.3556531"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":40,"alternative-id":["10.1145\/3552466.3556531","10.1145\/3552466"],"URL":"https:\/\/doi.org\/10.1145\/3552466.3556531","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}