Speech Recognition System For English Language

Abstract: This paper presents an overview of speech recognition technology. This report presents an overview of speech recognition technology, software, development and applications. It begins with a description of how such systems work, and the level of accuracy that can be expected. Present work is aimed at developing suitable speech recognition for hindi language, for the people who are physically hampered and cannot able to operate the computer through keyboard and mouse. In this paper we are using a HMM (hidden Markov model) to recognize speech samples to give excellent results for isolated words. It consists of isolated words that are separated by silences. The advantage of discrete speech is that word boundaries can be set exactly while with continuous speech; words will be spoken without silences.

Keywords: Speech Recognition, HMM, Discrete Speech