HMM (Hidden Markov Model) Based Speech to Text Conversion for Regional Language (TAMIL)

The conversion of speech to text for the regional language, TAMIL is being done using HMM (Hidden Markov Model). As the speech to text conversion is yet to be exploited in Tamil language, the purpose of converting speech to text for Tamil language becomes essential. Tamil is a highly inflectional language. The primary aim of this research is to understand the Tamil spoken word and convert it into Tamil text. The full-fledged conversion of all Tamil words through speech to text may be performed in the near future. In the first trial, only 25 familiar Tamil words have been identified, recognized through English, converted and displayed in Tamil text. This conversion of speech to text is done with the help of HMM (Hidden Markov Model) process for 25 Tamil words and the accuracy of conversion is found to be 83%.