期刊名称：International Journal of Computer Science and Security (IJCSS)
电子版ISSN：1985-1553
出版年度：2010
卷号：4
期号：3
页码：352-360
出版社：Computer Science Journals
摘要：One of the key components of Text to Speech Synthesizer is prosody generator. There are basically two types of Text to Speech Synthesizer, (i) single tone synthesizer and (ii) multi tone synthesizer. The basic difference between two approaches is the prosody feature. If the output of the synthesizer is required in normal form just like human conversation, then it should be added with prosody feature. The prosody feature allows the synthesizer to vary the pitch of the voice so as to generate the output in the same form as if it is actually spoken or generated by people in conversation. The paper describes various aspects of the design and implementation of speech synthesizer, which is capable of generating variable pitch output for the text. The concept of forward parsing is used to find out the emotion in the text and generate the output accordingly.
关键词：Text to Speech Synthesis; Forward Parsing; Emotion Generator; Prosody Feature
