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