Abstract
The goal of this project was to code and assemble a web browser with voice recognition abilities. The project aims to simplify the usage of a web browser. Existing web browsers are complicated to use and focus on feasibility but sometimes lack the user ease. Web browsers, i.e. Chrome, Firefox, and Safari come with voice recognition, but the web browser in this project extends user comfort and has additional features. In particular, this project creates a “Typing- free” experience for a web browser, so that the user is never required to type a web search address. The primary focus is for users with no hands or who have physical disabilities. This smart browser is equipped with natural language (English) recognition capabilities which extract the key commands from sentence. If user asks web browser “open new tab and search what is AI?”, the browser would open a new tab and search “what is AI?” using the default search engine which is “google.com”.WEBOICE is listening all the times and responds according to the user’s command. If the user asks WEBOICE to “open Facebook in a new window,” it will open a new window and then open Facebook. The browser is equipped with the traditional browser's functionalities such as forward, backward, stop navigation and the additional feature of motion recognition capabilities which will allow the user to have complete interactive environment. However, WEBOICE does have its limitations, it is not able to differentiate between words with very similar pronunciation i.e. “back/jack”; also it might take a while to execute depending on the speed of the connection with Google API.