Speech therapy system to Kannada language

Abstract

This paper presents an alternative communication technique to help people suffering from speech and language difficulties for various reasons. Electronic Speech synthesis is a process of generating human like speech from any text input to emulate human speaker. The objective of text to speech system is to convert an arbitrary Kannada text into its corresponding spoken waveform, using phoneme as basic unit for speech synthesis. A standard syllable level speech database consisting of 525 syllables is built for synthesizing naturally sounding speech. The main advantage of this system is the real time approach for conversion of entered text to corresponding speech. The initial and the final points of a speech waveform are determined using Maximum energy and zero crossing rate. The Unit selection based concatenation method is opted for syllable concatenation and the system is implemented using MATLAB.