Pitch and duration modification for expressive speech synthesis in Marathi TTS system

Generating expressive synthetic speech is very important in high quality Marathi Text-to-Speech (TTS) system. This paper focuses on voice conversion and modification technique maintaining acceptable quality and naturalness with reduced database. In this paper, a method to modify fundamental frequency contour is proposed for Marathi TTS system. The naturalness of the speech is highly correlated to phonetic description and prosodic features such as Fundamental frequency and duration of that phone. For prosody generation, we have obtained a primary pitch curve for the word, based on the location followed by punctuation marks. Question mark and exclamation mark in the text are studied to modify prosody. Phase-Vocoder technique can be used to improve the prosody of the synthesized speech. The experimental results showed that the proposed prosody modification, based on pitch and duration modification can improve speech quality.