Text to Speech Synthesis using Fraction Based Waveform Concatenation and Optimal Coupling Smoothing Technique

Text to Speech System is a Speech Synthesis application that converts a text to speech. The current project focuses on developing a TTS System for the Tamil Language with the Synthesis Technique as Unit Selection Synthesis. Letter Level Segmentation of an input text helps in the reduction of corpus size compared to Syllable Level Segmentation. The segmented units are retrieved with respect to Unicode values, concatenated and the synthesized speech is produced. Intelligibility and Naturalness of the spoken word can be improved using the Smoothing Techniques. Optimal Coupling Smoothing Technique is implemented for the smooth transition in between the concatenated speech segments to create continuous Speech output like human voice. Fraction based Waveform Concatenation method is used to produce the intelligible speech segments as output from the pre-recorded speech database.