Toward Efficient Low Cost Highly Accurate Emotion Speech Synthesizer,
Abstract: A Text to Speech (TTS) system with the ability to express emotions is an interesting technology that is still under development. There have been multiple proposals to simulate emotion so far, and there are multiple dimensions for assessment. No system guarantees high score in all of...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IJCSNS
2008
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/23644/ http://irep.iium.edu.my/23644/ http://irep.iium.edu.my/23644/1/Efficenet_speeech.pdf |
| Summary: | Abstract:
A Text to Speech (TTS) system with the ability to
express emotions is an interesting technology that is still
under development. There have been multiple proposals
to simulate emotion so far, and there are multiple
dimensions for assessment. No system guarantees high
score in all of these dimensions, this means that no
system works in a direction to get low computation load,
small database along with high accuracy and excellent
voice quality. After all of these qualities are relative and
fuzzy and there is no rigid grading system. In this paper
we will propose a new path for research that will work
toward improving all of the quality factors together, so
that future work can come up with a more optimum
solution for the emotional TTS systems. |
|---|