Duration modeling for text to speech synthesis system using festival speech engine developed for Malayalam language

摘要

This paper describes duration modeling in Text To Speech Synthesis (TTS) for Malayalam language using open source Festival TTS engine. Classification and Regression Tree (CART) based data-driven phoneme duration modeling is presented. A number of features are extracted for predicting the duration of phonemes. Objective evaluation test was conducted to evaluate the intelligibility of the synthesized speech by root mean squared error (RMSE) and correlation between actual and predicted durations. The objective evaluation of the model gave an RMSE of 0.1188 and a correlation of 0.9918.