HMM BASED HINDI SPEECH RECOGNITION

Abstract

Many times key board acts as a barrier between computer and the user. This is true especially for rural areas. We face big challenge in applying this high level specialist knowledge of computers to Community development projects like “Sarva Siksha Abhiyan” so as to quickly bridge the “digital divide”.This barrier can be major hindrance in delivering computer literacy efficiently. Fascinated by the “Hole in the wall” initiative by NIIT, I decided to work on Hindi Speech Recognition so that the users can explore a computer’s potential by interacting with it in their own language thus unlocking the flood gates of development especially for our teeming rural population. This led to start of my work on “HMM BASED HINDI SPEECH RECOGNITION”. The main purpose of this study is to perform speech recognition for isolated words in Hindi language. The railway speech corpus has been included for the study. The speech corpus consists of 207 words spoken by 40 different male, fe...