An Approach for Anonymous Spelling for Voter Write-Ins Using Speech Interaction

Abstract

Today, the technology used for voting does not fully address the issues that disabled voters are confronted with during elections. Every voter, regardless of disability, should be able to vote and verify his or her ballot during elections without the assistance of others. In order for this to happen, a universal design should be incorporated into the development of all voting systems. The research presented in this thesis embraces the needs of those who are disabled. The primary objective of this research was to develop a system in which a person, regardless of disability, can efficiently, anonymously, and independently write-in a candidate’s name during an election. The method presented here uses speech interaction and name prediction to allow voters to privately spell the name of the candidate they intend to write-in. A study was performed to determine the effectiveness and efficiency of the system. The results of the study showed that spelling a name using the predictive method developed is an effective and efficient solution to the aforementioned issues.