CHAPTER ONE

INTRODUCTION

1. 1. Background of the Study

Personal Recognition is required to secure the privacy of individual’s properties from unauthorized ones. In the past few decades, password or Personal Identification Number (PIN) has been used to fulfill the needs. This is an inconvenient way of personal recognition since people need to remember their PIN(s) and someone other than the authorized user can also use it (Hirsimaki et al., 2012).

Voice recognition is a method of personal recognition using biometric technology. Users only need to speak to a microphone and the system will extract the useful and unique information from their voice to recognize them. Hence it is more comfortable for users and more accurate than using fingerprint recognition. Hidden features of human voice can be defined as the features that cannot be directly measured, such as volume (soft or loud), pitch (high or low frequency) but first need to be processed in order to measure the value. Most of the time, the process needs to do some conversion of the voice input between time domain and frequency domain (Abdul et al., 2005).

With the rapid growth of mobile internet and smart phones, security shortcomings of mobile software and mobile data communication have shifted the focus to strong authentication. The existing user-id/password methodology, while tolerable for desktops and laptops, is inadequate for mobile use due to the difficulty of data entry on a small form factor device and a higher risk of the device getting in the hands of unauthorized users. Recent advances in voice biometrics offer great potential for strong authentication in mobile environments using voice. This is of particular interest in the financial and banking industry, where financial institutes are looking for ways to offer mobile customers flexible and easy authentication while maintaining security and significantly reducing fraudulent usage (Hagai et al., 2012).

Voice contains information that partially characterizes a particular speaker. The scientific field that uses this information to recognize a speaker by machine is called automatic speaker recognition. The most common applications are access protection to physical premises or securing remote services (especially telephone-based services). State-of-the-art automatic speaker recognition techniques rely on similarity measures across a set of recordings. These measures are based on acoustic parameters extracted with signal analysis techniques. They can take into account the statistical distributions for a particular speaker, the content of the message, and information about the environment and recording medium (Campbell, 2007).

1.2     Statement of the Problem

The authentication of users in various computerized platforms have been a major challenge. Many methods of authenticating users in various computerized platforms include the use of username and passwords, graphical password authentication and biometric authentication methods. Biometric technology is a promising technology that makes use of any specific and uniquely identifiable physical human characteristic. Utilizing biometrics for personal recognition is better than the previous method because biometrics links the event to a particular individual, which is secure, convenient, accurate, providing an audit trail and is becoming socially acceptable since it is inexpensive and comfortable to use. The most commonly used personal recognition using biometric technology is utilizing fingerprint. It has been implemented widely, such as to track criminals, to represent approval on legal documents (serve the same purpose as signature), etc. Fingerprint is secure, convenient, and unique for each person. The disadvantage of fingerprint recognition is that it leaves fingerprint mark on the device that is used to scan it. The placement of the fingerprint on the device affects the accuracy of the recognition. Most users are less comfortable if they need to dirty their fingers to do the recognition (example is the use of ink). These disadvantages make it less socially acceptable. Thus, a voice authentication system is been proposed.

1.3     Aim and Objectives of the Study

The aim of this research is to develop a soft computing framework for speech authentication (a case study of online banking sector) using google Application Programming Interface (API).

The objectives of the study are to;

1. i. Design a speech authentication system using Unified Model Language (UML) tools.
2. Develop a framework using google Application Programming Interface (API) to carryout voice authentication.
3. Evaluate the developed system for performance.

1.4     Significance of the Study

The soft computing framework for speech authentication will be of significant benefits to the banking sector, via the deployment of the developed system along online banking operations, which will in turn bring about more ease and less time in authenticating users via voice.

The software is relevant in the following ways:

1. The designed software will aid in carrying out voice authentication.
2. The designed software will reduce the time frame un authenticating a user since its via speech.
3. The system will serve as a conduit for further research by scholars and academicians.
4. The designed software will also be relevant to any individual or agency which will like to carry out a survey on performance of speech authentication system.

1.5     Scope of the Study

This research work covers the development of a system for speech authentication using google Application Programming Interface (API).

1.6 Definition of Terms

API: An application programming interface is a connection between computers or between computer programs. It is a type of software interface, offering a service to other pieces of software. A document or standard that describes how to build or use such a connection or interface is called an API specification.

Authentication: the process or action of proving or showing something to be true, genuine, or valid.

Computing: Computing is any goal-oriented activity requiring, benefiting from, or creating computing machinery. It includes the study and experimentation of algorithmic processes and development of both hardware and software. It has scientific, engineering, mathematical, technological and social aspects.

Framework: an essential supporting structure of a building, vehicle, or object.

Mobile App:  A mobile app or mobile application is a computer program or software application designed to run on a mobile device such as a phone-tablet or watch.

Recognition: identification of someone or something or person from previous encounters or knowledge.

Software: These are set of instructions that are designed to solve a specific problem. Software is made up of data and instructions. There are two categories of software; System software and Application software.

Speech Recognition: Speech recognition is an interdisciplinary subfield of computer science and computational linguistics that develops methodologies and technologies that enable the recognition and translation of spoken language into text by computers with the main benefit of searchability.

Speech: the expression of or the ability to express thoughts and feelings by articulate sounds.

System: A system is a set of detailed methods, procedures and routines created to carry out a specific activity, perform a duty, or solve a problem

Unified Modeling Language: The Unified Modeling Language is a general-purpose, developmental, modeling language in the field of software engineering that is intended to provide a standard way to visualize the design of a system.

Voice Authentication: Voice authentication is a form of identifying someone based on unique biometric characteristics - in this case, their voice. A voice is unique as a fingerprint and consists of a combination of characteristics such as dialect, pitch and speed.