Bengali Diphone Duration Modeling for Bengali Text to Speech Synthesis System

Abstract

This paper elaborates the analysis and implementation of a durational model of diphone for Bengali Text To Speech. Our analysis focused on duration of diphone according to several categories of consonant. Here we have proposed and implemented a durational model of diphone based on pronunciation place of consonant. This durational model is convenient to any diphone based Bengali Text to Speech Synthesizer. We have implemented our proposed durational model of diphone on Bengali Text To Speech synthesis software “Subachan”. Outcomes of this implementation is satisfactory. We have enhanced the overall performance of “Subachan” successfully with new diphone set.