{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T10:33:16Z","timestamp":1771929196003,"version":"3.50.1"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Speech Communication"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.specom.2026.103364","type":"journal-article","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T17:02:59Z","timestamp":1770397379000},"page":"103364","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Leveraging Kolmogorov-Arnold networks for voice liveness detection in anti-spoofing systems"],"prefix":"10.1016","volume":"178","author":[{"given":"Arth J.","family":"Shah","sequence":"first","affiliation":[]},{"given":"Madhu R.","family":"Kamble","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.specom.2026.103364_b1","doi-asserted-by":"crossref","unstructured":"Akimoto, K., Liew, S.P., Mishima, S., Mizushima, R., Lee, K.A., 2020. POCO: A Voice Spoofing and Liveness Detection Corpus Based on Pop Noise. In: INTERSPEECH. Shanghai, China, pp. 1081\u20131085.","DOI":"10.21437\/Interspeech.2020-1243"},{"key":"10.1016\/j.specom.2026.103364_b2","series-title":"2014 International Conference of the Biometrics Special Interest Group","first-page":"1","article-title":"Re-assessing the threat of replay spoofing attacks against automatic speaker verification","author":"Alegre","year":"2014"},{"key":"10.1016\/j.specom.2026.103364_b3","series-title":"Deep residual neural networks for audio spoofing detection","author":"Alzantot","year":"2019"},{"issue":"5","key":"10.1016\/j.specom.2026.103364_b4","doi-asserted-by":"crossref","first-page":"2698","DOI":"10.1121\/1.404385","article-title":"An efficient algorithm for the calculation of a constant Q transform","volume":"92","author":"Brown","year":"1992","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/j.specom.2026.103364_b5","series-title":"International Conference on Speech and Computer","first-page":"421","article-title":"Robustness of whisper features for infant cry classification","author":"Charola","year":"2023"},{"key":"10.1016\/j.specom.2026.103364_b6","series-title":"Interspeech","first-page":"102","article-title":"ResNet and model fusion for automatic spoofing detection.","author":"Chen","year":"2017"},{"key":"10.1016\/j.specom.2026.103364_b7","series-title":"The Speaker and Language Recognition Workshop","first-page":"296","article-title":"ASVspoof 2017 version 2.0: meta-data analysis and baseline enhancements","author":"Delgado","year":"2018"},{"key":"10.1016\/j.specom.2026.103364_b8","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1016\/j.neunet.2022.04.029","article-title":"ExSpliNet: An interpretable and expressive spline-based neural network","volume":"152","author":"Fakhoury","year":"2022","journal-title":"Neural Netw."},{"key":"10.1016\/j.specom.2026.103364_b9","doi-asserted-by":"crossref","first-page":"26951","DOI":"10.1007\/s11042-020-09281-y","article-title":"Voice liveness detection under feature fusion and cross-environment scenario","volume":"79","author":"Garg","year":"2020","journal-title":"Multimedia Tools Appl."},{"issue":"01","key":"10.1016\/j.specom.2026.103364_b10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1142\/S0219530522500129","article-title":"Deep ReLU neural networks overcome the curse of dimensionality for partial integrodifferential equations","volume":"21","author":"Gonon","year":"2023","journal-title":"Anal. Appl. (Singap.)"},{"key":"10.1016\/j.specom.2026.103364_b11","series-title":"2022 IEEE International Conference on Signal Processing and Communications","first-page":"1","article-title":"Morse wavelet features for pop noise detection","author":"Gupta","year":"2022"},{"key":"10.1016\/j.specom.2026.103364_b12","unstructured":"Gupta, P., Gupta, S., Patil, H.A., 2021, Kolkata, India.. Voice liveness detection using bump wavelet with CNN. In: 9th International Conference on Pattern Recognition and Machine Intelligence."},{"key":"10.1016\/j.specom.2026.103364_b13","series-title":"2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","first-page":"775","article-title":"Deep convolutional neural network for voice liveness detection","author":"Gupta","year":"2021"},{"key":"10.1016\/j.specom.2026.103364_b14","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1016\/j.csl.2023.101571","article-title":"Morse wavelet transform-based features for voice liveness detection","volume":"84","author":"Gupta","year":"2024","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.specom.2026.103364_b15","series-title":"On the optimal expressive power of relu dnns and its application in approximation with kolmogorov superposition theorem","author":"He","year":"2023"},{"key":"10.1016\/j.specom.2026.103364_b16","series-title":"Interspeech","first-page":"87","article-title":"Ensemble learning for countermeasure of audio replay spoofing attack in asvspoof2017.","author":"Ji","year":"2017"},{"key":"10.1016\/j.specom.2026.103364_b17","series-title":"2021 29th European Signal Processing Conference","first-page":"126","article-title":"Significance of constant-q transform for voice liveness detection","author":"Khoria","year":"2021"},{"key":"10.1016\/j.specom.2026.103364_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.csl.2022.101421","article-title":"On significance of constant-Q transform for pop noise detection","volume":"77","author":"Khoria","year":"2023","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.specom.2026.103364_b19","series-title":"The asvspoof 2017 challenge: Assessing the limits of replay spoofing attack detection","author":"Kinnunen","year":"2017"},{"key":"10.1016\/j.specom.2026.103364_b20","series-title":"Artificial Neural Networks\u2014ICANN 2002: International Conference Madrid, Spain, August 28\u201330, 2002 Proceedings 12","first-page":"474","article-title":"On the training of a Kolmogorov network","author":"K\u00f6ppen","year":"2002"},{"key":"10.1016\/j.specom.2026.103364_b21","series-title":"The kolmogorov superposition theorem can break the curse of dimensionality when approximating high dimensional functions","author":"Lai","year":"2021"},{"key":"10.1016\/j.specom.2026.103364_b22","series-title":"Interspeech 2015","article-title":"The RedDots data collection for speaker recognition","author":"Lee","year":"2015"},{"key":"10.1016\/j.specom.2026.103364_b23","series-title":"Image Processing: Concepts, Methodologies, Tools, and Applications","first-page":"54","article-title":"The kolmogorov spline network for image processing","author":"Leni","year":"2013"},{"issue":"1","key":"10.1016\/j.specom.2026.103364_b24","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1162\/neco.1993.5.1.18","article-title":"On the realization of a Kolmogorov network","volume":"5","author":"Lin","year":"1993","journal-title":"Neural Comput."},{"key":"10.1016\/j.specom.2026.103364_b25","series-title":"Kan: Kolmogorov-arnold networks","author":"Liu","year":"2024"},{"key":"10.1016\/j.specom.2026.103364_b26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neunet.2019.12.013","article-title":"Error bounds for deep ReLU networks using the Kolmogorov\u2013arnold superposition theorem","volume":"129","author":"Montanelli","year":"2020","journal-title":"Neural Netw."},{"key":"10.1016\/j.specom.2026.103364_b27","series-title":"Deep ReLU networks overcome the curse of dimensionality for bandlimited functions","author":"Montanelli","year":"2019"},{"key":"10.1016\/j.specom.2026.103364_b28","series-title":"Interspeech","first-page":"1111","article-title":"Investigating light-ResNet architecture for spoofing detection under mismatched conditions.","author":"Parasu","year":"2020"},{"key":"10.1016\/j.specom.2026.103364_b29","series-title":"INTERSPEECH","first-page":"12","article-title":"Novel variable length teager energy separation based instantaneous frequency features for replay detection.","author":"Patil","year":"2017"},{"key":"10.1016\/j.specom.2026.103364_b30","series-title":"Discrete-Time Speech Signal Processing: Principles and Practice","author":"Quatieri","year":"2002"},{"key":"10.1016\/j.specom.2026.103364_b31","series-title":"Odyssey 2016: The Speaker and Language Recognition Workshop","first-page":"259","article-title":"Voice liveness detection for speaker verification based on a tandem","author":"Shiota","year":"2016"},{"key":"10.1016\/j.specom.2026.103364_b32","doi-asserted-by":"crossref","unstructured":"Singh, M., 2021, Indonesia. A Survey on Linear Prediction Residual based Replay Attack Detection System. In: 2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS). pp. 14\u201317.","DOI":"10.1109\/IoTaIS50849.2021.9359690"},{"key":"10.1016\/j.specom.2026.103364_b33","doi-asserted-by":"crossref","unstructured":"Singh, S., Khoria, K., Patil, H.A., 2021, Dublin, Ireland. Modified group delay cepstral coefficients for voice liveness detection. In: 29Th European Signal Processing Conference. EUSIPCO, pp. 146\u2013150.","DOI":"10.23919\/EUSIPCO54536.2021.9616343"},{"issue":"1","key":"10.1016\/j.specom.2026.103364_b34","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/S0893-6080(01)00107-1","article-title":"Space-filling curves and Kolmogorov superposition-based neural networks","volume":"15","author":"Sprecher","year":"2002","journal-title":"Neural Netw."},{"issue":"3","key":"10.1016\/j.specom.2026.103364_b35","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1121\/1.1915893","article-title":"A scale for the measurement of the psychological magnitude pitch","volume":"8","author":"Stevens","year":"1937","journal-title":"J. Acoust. Soc. Am."},{"issue":"9","key":"10.1016\/j.specom.2026.103364_b36","doi-asserted-by":"crossref","first-page":"8257","DOI":"10.1109\/JIOT.2022.3230992","article-title":"A self-attentional ResNet-LightGBM model for IoT-enabled voice liveness detection","volume":"10","author":"Sun","year":"2022","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.specom.2026.103364_b37","doi-asserted-by":"crossref","first-page":"516","DOI":"10.1016\/j.csl.2017.01.001","article-title":"Constant q cepstral coefficients: A spoofing countermeasure for automatic speaker verification","volume":"45","author":"Todisco","year":"2017","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.specom.2026.103364_b38","doi-asserted-by":"crossref","unstructured":"Todisco, M., Wang, X., Vestman, V., Sahidullah, M., Delgado, H., Nautsch, A., Yamagishi, J., Evans, N., Kinnunen, T.H., Lee, K.A., 2019. ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection. In: INTERSPEECH. Graz, Austria, pp. 1008\u20131012.","DOI":"10.21437\/Interspeech.2019-2249"},{"issue":"3","key":"10.1016\/j.specom.2026.103364_b39","doi-asserted-by":"crossref","first-page":"1743","DOI":"10.3390\/s23031743","article-title":"Multi-input speech emotion recognition model using mel spectrogram and GeMAPS","volume":"23","author":"Toyoshima","year":"2023","journal-title":"Sensors"},{"key":"10.1016\/j.specom.2026.103364_b40","doi-asserted-by":"crossref","unstructured":"Wang, Q., Lin, X., Zhou, M., Chen, Y., Wang, C., Li, Q., Luo, X., 2019, Paris, France. Voicepop: A pop noise based anti-spoofing system for voice authentication on smartphones. In: IEEE Conference on Computer Communications. pp. 2062\u20132070.","DOI":"10.1109\/INFOCOM.2019.8737422"},{"key":"10.1016\/j.specom.2026.103364_b41","series-title":"Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific","first-page":"1","article-title":"A study on replay attack and anti-spoofing for text-dependent speaker verification","author":"Wu","year":"2014"},{"issue":"4","key":"10.1016\/j.specom.2026.103364_b42","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1109\/JSTSP.2017.2671435","article-title":"ASVspoof: the automatic speaker verification spoofing and countermeasures challenge","volume":"11","author":"Wu","year":"2017","journal-title":"IEEE J. Sel. Top. Signal Process."},{"issue":"2","key":"10.1016\/j.specom.2026.103364_b43","doi-asserted-by":"crossref","DOI":"10.1007\/s11704-022-2121-6","article-title":"Physiological-physical feature fusion for automatic voice spoofing detection","volume":"17","author":"Xue","year":"2023","journal-title":"Front. Comput. Sci."},{"key":"10.1016\/j.specom.2026.103364_b44","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.specom.2023.01.001","article-title":"Cross-modal information fusion for voice spoofing detection","volume":"147","author":"Xue","year":"2023","journal-title":"Speech Commun."},{"key":"10.1016\/j.specom.2026.103364_b45","series-title":"Deep convolutional neural networks","author":"Zhou","year":"1910"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639326000129?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639326000129?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T09:52:46Z","timestamp":1771926766000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639326000129"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":45,"alternative-id":["S0167639326000129"],"URL":"https:\/\/doi.org\/10.1016\/j.specom.2026.103364","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Leveraging Kolmogorov-Arnold networks for voice liveness detection in anti-spoofing systems","name":"articletitle","label":"Article Title"},{"value":"Speech Communication","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.specom.2026.103364","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103364"}}