Broad Acoustic Classification of Spoken Hindi Hybrid Paired Words using Artificial Neural Networks

Abstract

this paper, comparison of recognition rate on the basis of domination of vowel and consonant sound in Spoken Hindi Hybrid Paired Words (SHHPW) has been carried out, with 660 utterances as database; Linear Prediction Cepstral Coefficient (LPCC) is used as a feature extraction method and Artificial Neural Networks (ANN) as a classifier. It has been observed that Consonant dominated words provides better recognition rate as compared to vowel dominated words. Average recognition rate of 93.56% has been observed for the group with consonant dominated words on the considered data base.