BUILDING NEWSPAPER READING PROGRAM FOR BLIND

Abstract

Human communication today is mainly via speech and text. To access information in a text, a person needs to have vision. However those who are deprived of vision can gather information using their hearing capability. Speech regconition and speech synthesis technologies have been the subject of much interest in recent years, with the aim of building systems such as voice-controlled computers, voice input, the system helps people and computer can interact through voice...; however, equipment and software to support visually impaired people is still limited and not support Vietnamese. The proposal of the thesis is to use speech recognition technology and difflib module to build voice control functions; speech synthesis to build text-to-speech and parsing website content to build software that helps visually impaired people read online newspaper. Results show that speech recognition and text-to-speech technologies can be applied to build voice interactive applications, especially in support of visually impaired people.