期刊名称:Faculty of Computer Science and Information Technology
出版年度:2011
卷号:0
期号:0
语种:English
出版社:Faculty of Computer Science and Information Technology
摘要:ABSTRACT : Voice synthesizer system is a technique in which system converts text into voice signals. One technique used is a Diphone Concatenation technique in which sound segments in diphone voices had been previously recorded based on the prevailing roles in a language. In this technique, text will be synthesized based on the combined of diphoned text. Diphone in the Indonesian language may consist of phonemes combination which consists of vowel-vowel combination, consonant-consonant combination, vowel-consonant combination, or consonant-vowel combination. Each unit sound has different characteristics. In this article we will determine characteristics of sound signals for the vowel and consonant as a diphone engine on Indonesian speech synthesizer. Indonesian consonants have eight groups based on the form of similar pattern from spectrogram.