Abstract
Voice-based authentication can allow for straightforward and unobtrusive authentication with mobile devices. With COVID-19, wearing face masks has become common in many parts of the world. While prior research has shown that face masks act like low pass filters, the impact of face masks on voice-based authentication with mobile devices is still unclear. In this paper we analyze the impact of FFP2 masks on voice authentication for mobile devices in realistic scenarios. We evaluate a pretrained EPACA-TDDN speaker verification model with a self-recorded database of 450 mobile voice authentication utterances from 30 speakers, with a total length of 29 min. Results indicate that wearing FFP2 face masks has a slight but significant impact on speaker verification scores. Results also indicate that in authentication scenarios they lead to a slight increase of the FNR, and in comparison smaller decrease of the FPR, and in direct comparison, to a slight increase of the EER.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
- 2.
- 3.
Android version market share: https://gs.statcounter.com/android-version-market-share/mobile (Jul 2022).
References
Balamurali, B.T., Enyi, T., Clarke, C.J., Harn, S.Y., Chen, J.M.: Acoustic effect of face mask design and material choice. Acoust. Aust. 49(3), 505–512 (2021)
Bogdanel, G., Belghazi-Mohamed, N., Gómez-Moreno, H., Lafuente-Arroyo, S.: Study on the effect of face masks on forensic speaker recognition. In: Alcaraz, C., Chen, L., Li, S., Samarati, P. (eds.) Information and Communications Security, pp. 608–621. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-15777-6_33
Corey, R.M., Jones, U., Singer, A.C.: Comparison of the acoustic effects of face masks on speech. Hear. J. 74(1), 36–38 (2021)
Desplanques, B., Thienpondt, J., Demuynck, K.: ECAPA-TDNN: emphasized channel attention, propagation and aggregation in TDNN based speaker verification. In: Interspeech 2020. ISCA (2020)
Goldin, A., Weinstein, B., Shiman, N., et al.: How do medical masks degrade speech perception. Hear. Rev. 27(5), 8–9 (2020)
Gutz, S., Rowe, H., Green, J.: Speaking with a KN95 face mask: ASR performance and speaker compensation. Interspeech 2021, 4798–4802 (2021)
Khan, A., et al.: Toward realigning automatic speaker verification in the era of covid-19. Sensors 22(7), 2638 (2022)
Magee, M., et al.: Effects of face masks on acoustic analysis and speech perception: implications for peri-pandemic protocols. J. Acoust. Soc. Am. 148(6), 3562–3568 (2020)
Nagrani, A., et al.: VoxSRC 2020: the second VoxCeleb speaker recognition challenge. arXiv:2012.06867
Ngan, M., Grother, P., Hanaoka, K.: Ongoing face recognition vendor test (FRVT) part 6A: face recognition accuracy with masks using pre- COVID-19 algorithms (2020)
Nguyen, D.D., et al.: Acoustic voice characteristics with and without wearing a facemask. Sci. Rep. 11(1), 5651 (2021)
Pörschmann, C., Lübeck, T., Arend, J.M.: Impact of face masks on voice radiation. J. Acoust. Soc. Am. 148(6), 3663–3670 (2020)
Ravanelli, M., et al.: SpeechBrain: a general-purpose speech toolkit (2021). arXiv:2106.04624
Rui, Z., Yan, Z.: A survey on biometric authentication: toward secure and privacy-preserving identification. IEEE Access 7, 5994–6009 (2019)
Saeidi, R., Niemi, T., Karppelin, H., Pohjalainen, J., Kinnunen, T.H., Alku, P.: Speaker recognition for speech under face cover. In: Interspeech 2015 (2015)
Schwartz, J.C., Whyte, A.T., Al-Nuaimi, M., Donai, J.J.: Effects of signal bandwidth and noise on individual speaker identification. J. Acoust. Soc. Am. 144(5), EL447–EL452 (2018)
Smiljanic, R., Keerstock, S., Meemann, K., Ransom, S.M.: Face masks and speaking style affect audio-visual word recognition and memory of native and non-native speech. J. Acoust. Soc. Am. 149(6), 4013–4023 (2021)
Toscano, J.C., Toscano, C.M.: Effects of face masks on speech recognition in multi-talker babble noise. PLoS ONE 16(2), 1–12 (2021)
Wang, C., Wang, Y., Chen, Y., Liu, H., Liu, J.: User authentication on mobile devices: approaches, threats and trends. Comput. Netw. 170, 107118 (2020)
Zollinger, S.A., Brumm, H.: The Lombard effect. Curr. Biol. 21(16), R614–R615 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sedlak, D., Findling, R.D. (2023). On the Impact of FFP2 Face Masks on Speaker Verification for Mobile Device Authentication. In: Delir Haghighi, P., Khalil, I., Kotsis, G., ER, N.A.S. (eds) Advances in Mobile Computing and Multimedia Intelligence. MoMM 2023. Lecture Notes in Computer Science, vol 14417. Springer, Cham. https://doi.org/10.1007/978-3-031-48348-6_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-48348-6_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48347-9
Online ISBN: 978-3-031-48348-6
eBook Packages: Computer ScienceComputer Science (R0)