Di-Diphone Arabic Speech Synthesis Concatenation

Abstract

This work describes the new Arabic Text-to-speech (TTS) synthesis system. This system based on di-Diphone concatenation with TD-PSOLA modifier synthesizer. The quality of a synthesized speech is improved by analyzing the spectrum features of voice source in various F0 ranges and timbres in detail and new unites concatenation. It generates speech synthesis based on analysis and estimation of formant by classifying the voice source into different types. The developed model enhances the quality of the naturalness, and the intelligibility of speech synthesis in various speaking environment.