Pause duration model for Malayalam TTS

In this paper a CART-based pause duration prediction model has been developed for Malayalam language. Prosodic features like pause durations, syllable prolongations etc. play an important role in making the speech output from a Text To Speech (TTS) system more intelligible. An analysis on the various factors that affect pause duration for Malayalam language has not been conducted till date. Here, inferential and descriptive statistical analysis tools are used to analyze the effect of various factors on pause duration for Malayalam. These identified factors are then used to model pause duration for pause after a word, pause after a phrase, pause after a comma and pause after a sentence separately. The RMSE and correlation values are calculated to evaluate the correctness of the model.