Technically, speech synthesis is the conversion and output of coded data in the form of speech. For this purpose, speech synthesis systems store corresponding words or word fragments and classify them phonemically. When a certain code is recognized, words and sentences can be generated from this pool.
Two procedures are used in speech synthesis: the use of previously recorded natural speech in the form of phonemes, words and sentence fragments, and the generation of synthetic speech from data and text. While the first method can be used where a limited vocabulary is employed, synthetic generation works with an unlimited vocabulary. Such speech synthesis systems are used in computer telephony integration( CTI), call centers, directory assistance systems, screen readers, text-to-speech or e-mail-to-speech, the conversion of texts into speech.