Automatic speech recognition of isolated words in Hindi language

Speech recognition is a broad subject as speech is natural way of communication. The acoustic and language model for this system are available but mostly in English language [15]. In India there are so many peoples who can't understand or speak English. So the speech recognition system in English language is of no use for these people. Here we presented Isolated Hindi words recognition system which is a part of Automatic Speech Recognition (ASR) system. Automatic Speech Recognition (ASR) is also called as computer speech recognition. The main goal of ASR system understands a voice by computer or microphone and converts it into the text to perform required task. The performance accuracy of speech recognition is highly depends on feature extraction and pattern recognition technique. In this paper, we are using MFCC as feature extraction technique, K-Nearest Neighbor (KNN) with GMM (Gaussian Mixture Model) for recognition of Hindi isolated words. For practical analysis we will prepare the Hindi words speech dataset of different males and females speakers.