Abstract: “After years of research and development the accuracy of automatic speech recognition (ASR) remains one of the most important research challenges e.g. speaker and language variability, vocabulary size and domain, noise. The design of speech recognition system require careful attentions to the challenges or issue such as various types of speech classes, speech representation, feature extraction techniques, database and performance evaluation. This paper presents a study of basic approaches to speech recognition and their results shows better accuracy. This paper also presents what research has been done around for dealing with the problem of ASR”

Keywords: Automatic speech recognition, hidden markov model, acoustic model, MFCC