Speech Synthesis

Abstract

Speech synthesis is the artificial production of human speech. A system used for this purpose is termed a speech synthesizer, and can be implemented in software or hardware. Speech synthesis systems are often called text-to-speech (TTS) systems in reference to their ability to convert text into speech. However, systems exist that instead render symbolic linguistic representations like phonetic transcriptions into speech. A text-to-speech system is composed of two parts: a front-end and a back-end. Broadly, the front-end takes input in the form of text and outputs a symbolic linguistic representation. The back-end takes the symbolic linguistic representation as input and outputs the synthesized speech waveform . TTS software can "read" text from a document, Web page or e-Book, generating synthesized speech through a computer's speakers. TTS can also convert text files into audio MP3 files that can then be transferred to a portable MP3 player or CD-ROM. This can save time by allowing the user to listen to reports or background materials while performing other tasks. TTS makes a critical difference to those with disabilities such as poor vision or visual dyslexia. People with speech loss can utilize specialized TTS programs to turn typed words into vocalization. TTS programs provide a valuable edge, particularly for learning new languages. This thesis aims to study the speech synthesis technology and to develop a cost effective, user friendly text to speech conversion system using Laboratory virtual instruments engineering workbench (LabVIEW) graphical programming language.