You have no items in your shopping cart.
ABSTRACT
The ability to express one's thoughts through a set of signs (text), gestures, and noises is referred to as language. It is a distinguishing characteristic of humans, who are the only creatures who use such a system. Speech is the earliest and most extensively utilized method of inter-personal communication. The artificial fabrication of human speech is known as 'speech synthesis,' also known as 'Text to speech synthesis.' A voice synthesizer is a computer system that can be used for this purpose and can be developed in software. A text-to-speech (TTS) system simply turns written text into spoken language. Since the early 1990s, many computer operating systems have featured voice synthesizers. Although recent advances in speech synthesis have resulted in synthesizers with extremely high intelligibility, sound quality and naturalness remain a serious issue. However, the quality of current devices has improved to the point that they are suitable for a variety of applications, including multimedia and telecommunications. The following thesis gives a quick introduction of the key text-to-speech synthesis issues, as well as the preliminary work done in developing an English TTS.
