Identification of Goalparia dialect and similar languages

Accurate dialect identification technique helps in improving the speech recognition systems that exist in most of the electronic devices today and is also expected to help in providing new services in the field of e-health and telemedicine. In this paper, we describe a method to identify not just Goalparia dialect but also the languages it is similar to i.e. Assamese and Bengali. Mel Frequency Cepstral Coefficient (MFCC) has been used to extract the spectral features of the collected speech data. Gaussian Mixture Model (GMM) and Gaussian Mixture Model with Universal Background Model (GMM-UBM) have been used as the modeling techniques.