Human languages can be broadly divided into two categories: Tonal and Non-Tonal Languages. The basic difference is that tonal languages use pitch as a figure of speech, i.e. a change of pitch can alter the meaning of a word. In tonal languages, the way in which a word is uttered is very important. Also, tonal languages generally have higher pitch and pitch range than non-tonal languages. Speech signal contains both speaker and language characteristics. We extract some of these features and represent them through mathematical models. Then these features are fed to the various classifiers. In this paper, we analyze the efficiency of different classifiers to identify Tonal and Non-Tonal languages. The classifiers used are: Neural Network, k Nearest Neighbour Algorithm and Support Vector Machines.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.