Docstoc

Korean Text To Speech

Document Sample
Korean Text To Speech Powered By Docstoc
					Korean Text To Speech
- Jinseok Nam, University Of Waterloo


Speech is the primary method of communication between people. Speech synthesis has
been under research and development for several decades now. As the processing
power and memory resource increase, there will be more demands for speech related
technologies. In its current state, speech synthesis is being applied to many different
systems such as multimedia, telecommunication, and embedded systems. However, it
still poses some problems with naturalness and sound quality. A formant-based synthesizer
is small enough to be operated on embedded systems, where memory space and processor
speed are constrained. Additionally, because a formant synthesizer has total control over
all aspects of the output speech, it can easily manipulate parameters to modify the duration,
pitch, and volume. Therefore, it is much more flexible than other methods of speech
synthesis, such as articulatory and concatenative synthesis.

				
DOCUMENT INFO
Shared By:
Categories:
Tags:
Stats:
views:21
posted:6/5/2010
language:English
pages:1