A comparison of Gaussian Mixture Modeling (GMM) and Hidden Markov Modeling (HMM) based approaches for Automatic Phoneme Recognition in Kannada

Abstract

We build and compare phoneme recognition systems based on Gaussian Mixture Modeling (GMM) which is a static modeling scheme and Hidden Markov Modeling (HMM) which is a Dynamic modeling scheme. Both models were built by using Stochastic pattern recognition and Acoustic phonetic schemes to recognise phonemes. Since our native language is Kannada, a rich South Indian Language, we have used 15 Kannada phonemes to train and test these models. Since Mel — Frequency Cepstral Coefficients (MFCC) are well known Acoustic features of speech, we have used the same in speech feature extraction. Finally performance analysis of both models in terms of Phoneme Error Rate (PER) justifies the fact that Dynamic modeling yields better results over Static modeling and can be used in developing Automatic Speech Recognition systems.