in Japanese
Demonstrations
•Text-to-Speech Synthesis with Arbitrary Speaker's Voice
Average-Voice-Based Speech Synthesis: Text-to-speech synthesis with arbitrary speaker's voice
HSMM-based MLLR Adaptation
(QuickTime Movie 4.8MB)
Speaker Adaptive Training & Shared-Tree-based Clustering
(QuickTime Movie 1.6MB)
Various Speaker's Voice
(QuickTime Movie 3.6MB)
Comparison of Speaker Adaptation Techniques for Average-Voice-Based Speech Synthesis
Various Speaking Styles and Emotional Expressions
Speech synthesis with various voice characteristics and speaking styles
Style Interpolation and Style Morphing
Style Adaptation
Style Control
Speaker and Style Adaptation Using Average Voice Model for Style Control
Voice Quality Control of Synthetic Speech
A Technique for Controlling Voice Quality of Synthetic Speech Using Multiple Regression HSMM
•Text-to-Speech Synthesis for Thai
HMM-based Thai Speech Synthesis System
•Animation Synthesis
Hand-guesture
Human Walking Motion Synthesis
•Multi-modal Interface
Word pronunciation (QuickTime Movie 363KB)
Sentence pronunciation (QuickTime Movie 2,014KB)
Recent Topics
Top page