A review on selection and correction of text and speech data for Indian languages

Abstract

Today the word is going towards hands-free
interfacing with machine using speech commands and/or
speech recognition. The computer understands binary or
machine level language and human being communicate in
their own different - different languages so to make
machine capable of understanding the language behavior
their respective language model is been developed. To
develop the language model this paper focuses on the
selection and correction of text and speech data for some of
the Indian languages like Hindi, Indian English, Tamil,
Telugu, and Marathi.