Interaction evaluation of a mobile voice authentication system

Abstract

Abstract-Biometric recognition is nowadays widely used in smartphones, making the users' authentication easier and more transparent than PIN codes or patterns. Starting from this idea, the EU project PIDaaS aims to create a secure authentication system through mobile devices based on voice and face recognition as two of the most reliable and user-accepted modalities. This work introduces the project and the first PIDaaS usability evaluation carried out by means of the well-known HBSI model. In this experiment, participants interact with a mobile device using the PIDaaS system under laboratory conditions: video recorded and assisted by an operator. Our findings suggest variability among sessions in terms of usability and feed the next PIDaaS HCI design.

Voice and face interaction evaluation of a mobile authentication platform

“…Furthermore, the HBSI framework defines metrics related to usability (satisfaction, eefficiency and effectiveness), cognitive (learnability and memorability), ergonomics (physical conditions) and signal processing (sample quality and processing capabilities) [4] to obtain a holistic view of the user's interaction with the biometric system. For further details about the HBSI please refer to [2][3][4][5][6][7]. This framework has been tested for a number of different modalities: hand geometry [5], fingerprint [4] and face [6].…”

“…The HBSI has also been applied to mobile implementations for dynamic signature [7]. A novel and extended implementation was proposed in our previous work [2,8] which incorporates mobile analytic tools and server logs to ensure sufficient data is captured.…”

“…The experimental scenario set-up is based on our previous experiment [2] and the implementation lessons learnt. The main aim of the set-up is to recreate realistically an office environment.…”

“…A correct voice presentation was defined using the same description as in our previous experiment (refer to [2]). A correct face presentation occurs when the user places the head within the silhouette displayed within the capture interface.…”

“…In order to ensure the usability and effective interaction with the final PIDaaS Mobile Application (PMA), the Human-Biometric-Sensor Interaction (HBSI) framework using the integration proposed in our previous work [2] has been applied to a new version of the PMA to analyse how users interact with the different interfaces and enhance both the usability and the biometric performance of the final version of the system. As a continuation of the work presented in the 2016 ICCST Conference [2], the novel and extended HBSI framework proposed has been applied for the evaluation of a multi-modal biometric system, since the new version of the PMA integrates face and voice authentication. This experiment allowed a thorough comparison between face and voice biometric modalities from the same population.…”