Abstract:
One of the major drawbacks, especially for physically handicapped persons, of computers and electronic devices available nowadays is that they are not capable of human-like interaction. One emerging technology that gives these devices a way to interact with its users in a human-like fashion is speech recognition.
Voice recognition is the process of taking the spoken word as an input to a computer program. This process is important to virtual reality because it provides a fairly natural and intuitive way of controlling the simulation while allowing the user's hands to remain free. This project completely and comprehensively explains the procedure and path adopted towards the designing and development of a small-scale speaker dependent voice recognition system that can understand a limited number of commands and perform corresponding desired operations.
To further simplify the understanding of this project tables, figures are also provided. In this project it is explained in elaborated fashion that how to acquire data through a sound card using a mic, passing it through a band pass filter, using the filtered data for isolated word detection, its speech coding and finally its classification.
