Abstract
The number of cybercrimes in infocommunications area is growing, and they are becoming more sophisticated. According to the Cisco 2018 Annual Cybersecurity Report, spreading malicious software (in particular, ransomware), the volume of encrypted web traffic transmitted by cybercriminals, and the number of e-mail threats have increased. To protect financial and information resources pin codes, passwords, identification cards are used; however, they can be lost or counterfeited. Biometric authentication is now a solution these problems. Initially, static biometric features (fingerprints, face shape and size, iris and retina patterns) were mostly used, especially in forensic science. Due to simple forgery and limited amount of analyzed data in access systems, preference is given to behavioral biometric features, especially to the user voice signal. Voice systems are preferred by the efficiency/cost criterion. Moreover, voice systems have additional advantages: simplicity, ease of use, complexity of counterfeiting, remote use through communication channels, unlimited operational increase in password phrases, and the availability of digital data processing achievements. Unfortunately, the qualitative characteristics of voice authentication systems yield to systems which use static biometric features because the formation of a user's template is based on amplitude and frequency information. One of the directions for improving the quality indicators of voice authentication systems, according to the authors, is to use phase information of registration materials, which has not been sufficiently considered in the scientific literature. The object of research is the process of digital processing of speech signals in voice authentication systems. Research methods include analysis, observation, measurement, modeling and experiment. The paper considers the procedures for the formation and direction of voice signal phase data use in authentication systems. The feasibility of phase data use, which allows to improve qualitative indicators of the considered systems, is essentially proved on the example of processing experimental voice signals.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.