Clustering of Feature Vectors and Recognition of Bodo Phoneme Using MLP Technique

Abstract

The process through which a computer can identify spoken words is termed as speech recognition. After analysis and finding of features of the speech sound, one can go towards the recognition of the speech. The extraction of feature vector is known as the feature extraction process or the front-end process. This front-end process is considered as the 1st stage of speech recognition. Pattern matching process is the 2nd stage or final stage of speech recognition where actual search is carried out to decode the spoken utterances by matching the sequence of feature vectors against the acoustic and language models stored in the recognizer. To reduce this problem, clustering technique is used. Clustering makes it possible to look at properties of whole clusters instead of individual objects - a simplification that might be useful when handling large volume of data. Clustering is nothing but the assignment of a set of observations into subsets so that the observations in the same cluster are similar in some sense.