PHONEME BASED TEXT TO SPEECH SYSTEM FOR PUNJABI By Mnapreet Kaur,cse
Abstract
In recent years, the use of computers in speech synthesis and speech recognition has become an important area of study among speech and computer scientists. The primary motive is to provide users with a friendly vocal interface with the computer and to allow people with certain handicaps (such as blinds) to use the computer. In this thesis, work is concerned with the development of Text-To-Speech (TTS) Synthesis System for Punjabi text, written in Gurmukhi script. Punjabi is the world’s 12th most widely spoken language. The populace speaking Punjabi is not only confined to North Indian states of India such as Punjab, Haryana and Delhi but is spread in over all parts of the world. Punjabi is a phonetic language and commonly written in Gurmukhi script. The research work was carried out with the aim that the developed system must produce synthetic speech corresponding to two qualities of Speech Synthesis: intelligibility and naturalness. In order to get the naturalness in the synthetic speech, Concatenative speech synthesis techniques have been used, with Punjabi Phoneme as a basic unit. The total Punjabi Phonemes were analyzed over a carefully selected Punjabi corpus and the valid phonemes were selected. The Punjabi speech database was prepared by labelling phoneme sounds in the recorded sound file; and then storing, starting and ending point’s boundary values in the database. A fairly good quality Punjabi Text-To-Speech synthesis speech has been developed.
