Research Group of Human Computor Speech Interactive(Tsinghua)

Research Orientation

1. Speech Synthesis

  • Text Analysis
  • Prosody Modeling(韵律建模)
  • Prosody Prediction(韵律预测)
  • Emotion Synthesis(情感合成)
  • Speechc Platform
  • Embeded Speechc Synthesis
  • Multi-Langual Speech Synthesis
  • Text-to-Visual Speech(TTVS)

2. Speechc Analysis

  • Speech Corpus
  • Speech Labeling
  • Prosody Labeling
  • Prosody Computing(Computational Prosody)
  • Timbre Simulation/Conversion(音色模拟)

3. Biometrics

  • Speeker Recognition(Voice-print Recognition)
  • Fingerprint Recognition
  • Lip-movement Recocgnition
  • Chinese Viseme
  • Face Synthesis
  • Identity Identification/Verifaction
  • Security Control

4.Context based Infomation Retrieval

  • Feature Analysis
  • Audio Retrieval

你可能感兴趣的:(search)