Implementation of speech synthesis based on HMM using PADAS database

This paper describes the Arabic system synthesis on hidden Markov models (HTS). The main objective of Text-to-Speech (TTS) synthesis is to convert arbitrary input text to intelligible and natural sounding speech. Our developed synthesis system uses phonemes as HMM synthesis unit. In this work, the Phonetic Arabic Database Automatically Segmented “PADAS” based on rich phonetic and balanced speech corpus is used. Prosody is applied which makes the synthesized speech sound more like human speech. In order to reduce the synthetic quality, STRAIGHT system used into the system. Besides that basic setup, a high-quality analysis/ synthesis system STRAIGHT was employed for more sophisticated speech representation. This method has several advantages. As it is parametric, it is possible to play on the HMM parameters, change the producer voice characteristics. The developed model improves the speech synthesis, naturalness and intelligibility quality in the Arabic language environment.