期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2015
卷号：3
期号：9
DOI：10.15680/IJIRCCE.2015. 0309075
出版社：S&S Publications
摘要：Text-to-speech (TTS) is the generation of synthesized speech from text. Our goal is to make synthesizedspeech as intelligible, natural and pleasant to listen, as human speech. Speech is the primary means of communicationbetween people. During synthesis very small segments of recorded human speech are concatenated together to producethe synthesized speech. The quality of a speech synthesizer is judged by its similarity to the human voice and by itsability to be understood. A text-to-speech synthesizer allows people with visual impairments and reading disabilities tolisten to written works on a home computer. Many computer operating systems have included speech synthesizers sincethe early 1990s. Recent progress in speech synthesis has produced synthesizers with very high intelligibility but thesound quality and naturalness still remain a major problem. However, the quality of present products has reached anadequate level for several applications, such as multimedia and telecommunications. The following thesis presents abrief overview of the main text-to-speech synthesis problems, and the initial work done in building a TTS in English.
