Affiliation:
1. Dept. of ECE, BNM Institute of Technology, Bengaluru, India.
Abstract
There are number of languages around the world and knowing all the languages is very difficult for any person. At the same
time, unawareness about the language will hinder communication. Language identification is the process where the identifying the
language(s) in text form is performed based on the writing style and looking at the unique diacritics of each language. When a multitude
of languages are spoken in any circumstances, the first step in communication is the identification of the language. There are several
techniques used for language detection like machine learning and deep learning. These are used in detecting languages like German. In
India, numerous languages are spoken by the people and thus we propose to develop a model that detects two languages: Kannada and
Devanagari/Sanskrit. In this study, Support Vector Machines classifiers were used, for classification and an accuracy of 99% was
achieved.
Subject
Electrical and Electronic Engineering,Condensed Matter Physics,Instrumentation,Electronic, Optical and Magnetic Materials,Genetics,Animal Science and Zoology,Ecology, Evolution, Behavior and Systematics,Aquatic Science,General Medicine,General Mathematics,Mechanics of Materials,Biomedical Engineering,Biomaterials,Mechanics of Materials,Materials Science (miscellaneous),Mechanical Engineering,Mechanics of Materials,Condensed Matter Physics,General Medicine,Library and Information Sciences,Health Informatics