The goal of this study was to design a system that would facilitate word processing for the handicapped, and implement the general public's most natural and effective way of communication--verbally. The word processor recognized the letters of the alphabet. This project explored and tested three methods of feature extraction which were the DFT, Spectrogram, and MFCCs. It was shown that the MFCC provides the best feature vector with a recognition rate of 97.9%.
Worcester Polytechnic Institute
Major Qualifying Project
Access to this report is limited to members of the WPI community. Please contact a project advisor or their department to request access
Restricted-WPI community only
Electrical and Computer Engineering