Development of speech corpora for Goalparia dialect and similar languages

Abstract

Accurate dialect identification technique helps in improving the speech recognition systems that exist in most of the present day electronic devices and is also expected to help in providing new services in the field of e-health and telemedicine which is especially important for older and homebound people. The accuracy of a dialect identification system is highly dependent on its speech corpora. Therefore, in this paper, we describe how speech corpora have been developed for Goalparia dialect and languages it is similar to i.e. Assamese and Bengali. Finally, identification of Goalparia dialect, Assamese and Bengali languages have been done using the developed speech corpora in order to evaluate it.