DEVELOPMENT OF SPEECH TO FILIPINO SIGN LANGUAGE FOR THE DEAF OR MUTE FILIPINOS USING HIDDEN MARKOV MODEL (HMM)

摘要

The main purpose of this project is to design and develop a software based computer program that will convert Filipino Speech into its equivalent Sign Language. This program will run in the personal computer through MATLAB and will use Hidden Markov Model (HMM) as speech recognition engine that uses a MFCC coefficient in improving the speech feature representation in a HMM based recognition speech. It uses 7 state left-to-right model and a word-based model for a small scale vocabulary speech recognition. This study involves testing the system's speech recognition reliability and accuracy in which it is indicated in the objectives of the project. The study want to prove HMM still a high accuracy technique for image processing. The analysis is expected to meet the 85% reliability of the speech recognition of the system proposed in the objective.