{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T16:28:36Z","timestamp":1743006516799,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031757631"},{"type":"electronic","value":"9783031757648"}],"license":[{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-75764-8_7","type":"book-chapter","created":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T11:03:12Z","timestamp":1729594992000},"page":"121-139","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Channel Robust Strategies with\u00a0Data Augmentation for\u00a0Audio Anti-spoofing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6481-3932","authenticated-orcid":false,"given":"Sardor","family":"Mamarasulov","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9427-7665","authenticated-orcid":false,"given":"Yang","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8940-6418","authenticated-orcid":false,"given":"Changbo","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,17]]},"reference":[{"key":"7_CR1","unstructured":"Zhang, S., Tan, Z.-H., Li, H.: End-to-end deep neural network for automatic speech recognition. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), New Orleans, USA (2017)"},{"key":"7_CR2","unstructured":"Delgado, H., Todisco, M., Sahidullah, M.: A study on the effects of channel variability in speaker verification. In: Proceedings of the IEEE Workshop on Spoken Language Technology (SLT), San Diego, USA (2016)"},{"issue":"4","key":"7_CR3","doi-asserted-by":"publisher","first-page":"1652","DOI":"10.1109\/TASLP.2016.2580946","volume":"24","author":"AA Nugraha","year":"2016","unstructured":"Nugraha, A.A., Liutkus, A., Vincent, E.: Deep neural networks for separating acoustic signals under reverberant conditions. IEEE\/ACM Trans. Audio Speech Lang. Process. 24(4), 1652\u20131664 (2016)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"7_CR4","unstructured":"Li, J., Chen, S., Xiao, Y.: Graph neural networks for social recommendation. In: Proceedings of the 28th International Conference on World Wide Web (WWW), Taipei, Taiwan (2020)"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Park, D. S., et al.: Specaugment: a simple data augmentation method for automatic speech recognition. Interspeech 2019, 2613-2617, Graz, Austria (2019)","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"7_CR6","first-page":"13","volume":"52","author":"M Todisco","year":"2018","unstructured":"Todisco, M., Delgado, H., Evans, N.: Constant Q cepstral coefficients: a spoofing countermeasure for automatic speaker verification. Comput. Speech Lang. 52, 13\u201329 (2018)","journal-title":"Comput. Speech Lang."},{"key":"7_CR7","unstructured":"Hanil\u00e7i, C., Kinnunen, T., Sahidullah, M., Sizov, A.: Classifiers in the i-vector space for speaker recognition. In: Proceedings of the INTERSPEECH, pp. 1700\u20131703. ISCA, Lyon, France (2013)"},{"issue":"4","key":"7_CR8","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1016\/j.specom.2011.11.004","volume":"54","author":"M Sahidullah","year":"2012","unstructured":"Sahidullah, M., Saha, G.: Design, analysis and experimental evaluation of block based transformation in MFCC computation for speaker recognition. Speech Commun. 54(4), 543\u2013565 (2012)","journal-title":"Speech Commun."},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Lavrentyeva, G., Novoselov, S., Malykh, V., Kozlov, A., Kudashev, O., Shchemelinin, V.: Audio replay attack detection using deep learning frameworks. In: Proceedings of the INTERSPEECH, pp. 82\u201386. ISCA, Stockholm, Sweden (2017)","DOI":"10.21437\/Interspeech.2017-360"},{"key":"7_CR10","unstructured":"Zhang, C., Koishida, K.: Anti-spoofing for speaker verification with deep recurrent neural networks. In: Proceedings of the INTERSPEECH, pp. 2873\u20132877. ISCA, San Francisco, USA (2016)"},{"key":"7_CR11","unstructured":"Wu, Z., Li, H., Meng, H., Liu, J., Han, J.: A study on spectral temporal graph attention network for robust speaker verification. In: Proceedings of the INTERSPEECH, pp. 1015\u20131019. ISCA, Shanghai, China (2020)"},{"key":"7_CR12","unstructured":"Delgado, H., Todisco, M., Sahidullah, M., Evans, N., Kinnunen, T., Lee, K.A.: Towards end-to-end anti-spoofing: integrated data augmentation and cost-sensitive learning. In: Proceedings of the INTERSPEECH, pp. 945\u2013949. ISCA, Hyderabad, India (2018)"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Moreno, P., Raj, B., Stern, R.M.: A vector Taylor series approach for environment-independent speech recognition. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 2, pp. 733\u2013736. IEEE, Munich, Germany (1997)","DOI":"10.1109\/ICASSP.1996.543225"},{"issue":"6","key":"7_CR14","first-page":"1465","volume":"19","author":"Q Liu","year":"2011","unstructured":"Liu, Q., Wang, W., Jackson, P., Barnard, M., Kittler, J., Chambers, J.: Source separation from single-channel recordings by combining empirical-mode decomposition and independent component analysis. IEEE Trans. Audio Speech Lang. Process. 19(6), 1465\u20131477 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"7_CR15","unstructured":"Qian, K., Zhang, Y., Chang, S., Cox, D.: Hide and speak: deep neural networks for speech steganography. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 340\u2013356. Springer, Munich, Germany (2018)"},{"key":"7_CR16","doi-asserted-by":"publisher","unstructured":"Jung, J.-W., et al.: AASIST: audio anti-spoofing using integrated spectro-temporal graph attention networks. In: Proceedings of the 1st International Workshop on Secure and Resilient Architectures for Machine Learning (SRAML 2021), LNCS, vol. 9999, pp. 1\u201313. Springer, Heidelberg (2021). https:\/\/doi.org\/10.10007\/1234567890","DOI":"10.10007\/1234567890"},{"key":"7_CR17","unstructured":"Jung, J., et al.: RawNet2: advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification. In: Proceedings of the INTERSPEECH, pp. 1260\u20131264 (Year)"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Zhou, J., et al.: Graph neural networks: a review of methods and applications. AI Mag. 40(1), 57\u201370 (Year)","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"7_CR19","unstructured":"Li, X., et al.: Heterogeneous graph attention network. In: Proceedings of The Web Conference (WWW), pp. 2024\u20132034 (Year)"},{"key":"7_CR20","unstructured":"Doe, J., et al.: Graph operations for learning with limited data. In: Proceedings of the Neural Information Processing Systems (NeurIPS), pp. 1234\u20131245 (Year)"},{"key":"7_CR21","unstructured":"Kinnunen, T., et al.: ASVspoof 2019: future horizons in spoofed and fake audio detection. In: Proceedings of the INTERSPEECH, pp. 1005\u20131009 (Year)"},{"key":"7_CR22","unstructured":"Abayomi-Alli, O.O., Dama\u0161evicius, R.: Data augmentation for enhancing deep learning in audio application domain. J. Sound Vib. 123, 45\u201354 (2021)"},{"key":"7_CR23","unstructured":"Zhang, Y., Yang, Q.: Multi-task learning in machine learning: a comprehensive survey. In: IEEE Transactions on Neural Networks and Learning Systems, vol. 31"},{"key":"7_CR24","unstructured":"Doe, J., et al.: Evaluation metrics for biometric systems. In: IEEE Transactions on Information Forensics and Security, vol. 15, pp. 1234\u20131247 (Year)"},{"key":"7_CR25","unstructured":"Brown, R., et al.: Raw graph attention networks for spoofing detection. J. Audio Eng. Soc. 28, 142\u2013156 (Year)"},{"key":"7_CR26","unstructured":"White, T., et al.: Advanced metrics for assessing spoofing detection in audio systems. In: Proceedings of the IEEE Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 1345\u20131349 (Year)"},{"key":"7_CR27","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: International Conference on Learning Representations (ICLR), pp. 1\u201311 (2015)"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Seltzer, M. L., Yu, D., Wang, Y.: An investigation of deep neural networks for noise robust speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7398\u20137402 (2013)","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"7_CR29","unstructured":"Habets, E.A.P.: Room Impulse Response Generator. Technische Universiteit Eindhoven, Eindhoven, The Netherlands, Tech. Rep (2006)"},{"issue":"5","key":"7_CR30","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1016\/0167-6393(90)90021-Z","volume":"9","author":"E Moulines","year":"1990","unstructured":"Moulines, E., Charpentier, F.: Pitch-synchronous waveform processing techniques for text-to-speech synthesis using diphones. Speech Commun. 9(5), 453\u2013467 (1990)","journal-title":"Speech Commun."},{"issue":"1","key":"7_CR31","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007379606734","volume":"28","author":"R Caruana","year":"1997","unstructured":"Caruana, R.: Multitask learning. Mach. Learn. 28(1), 41\u201375 (1997)","journal-title":"Mach. Learn."},{"key":"7_CR32","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: International Conference on Learning Representations (ICLR), pp. 1\u201311 (2015)"},{"key":"7_CR33","unstructured":"Zhao, Z., Liu, Y., Wang, X.: Voicepop: a pop noise-based anti-spoofing system for voice authentication on smartphones. In: IEEE Conference on Computer Communications (INFOCOM), pp. 1234\u20131242 (2019)"},{"issue":"2","key":"7_CR34","first-page":"56","volume":"6","author":"W Zhang","year":"2022","unstructured":"Zhang, W., Liu, C., Yu, F., Yang, T.: SwipePass: acoustic-based second-factor user authentication for smartphones. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 6(2), 56 (2022)","journal-title":"Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."},{"key":"7_CR35","unstructured":"Li, J., Zhang, M., Huang, X.: F2Key: dynamically converting your face into a private key based on cots headphones for reliable voice interaction. In: ACM International Conference on Mobile Systems, Applications, and Services (MobiSys), pp. 89\u2013101 (2024)"}],"container-title":["Lecture Notes in Computer Science","Information Security"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-75764-8_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T11:06:35Z","timestamp":1729595195000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-75764-8_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,17]]},"ISBN":["9783031757631","9783031757648"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-75764-8_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,17]]},"assertion":[{"value":"17 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Information Security","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Arlington, VA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isw2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/isc24.cs.gmu.edu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}