RECOGNITION OF VERNACULAR LANGUAGE SPEECH FOR DISCRETE WORDS USING LPC TECHNIQUE

Abstract

Vernacular language spoken in various countries creates a limitation on software associated with speech recognition. This paper is an attempt to overcome such problem. The suggested work makes use of Linear Predictive Technique for better interpretation of spoken words. The rule based structure of fuzzy suits very well with closeness of vernacular speech recognition. In this paper we study the feasibility of Speech Recognition with fuzzy neural Networks for discrete Words Different Technical methods are used for speech recognition. Most of these methods are based on transfiguration of the speech signals for phonemes and syllables of the words. We use the expression "word Recognition" (because in our proposed method there is no need to catch the phonemes of words.). In our proposed method, LPC coefficients for discrete spoken words are used for compaction and learning the data and then the output is sent to a fuzzy system and an expert system for classifying the conclusion. The experimental results show good precisions. The recognition precision of our proposed method with fuzzy conclusion is around 90 percent.

Keywords: Vernacular, Words Recognition, Linear Predictive Coding, Feature Extraction, Automatic Speech Recognition, LPC Coefficients, Word error rate