Welcome to Henry Hao Tang's Personal Web Site

Some demos & screen snapshots of my work:

  • An expressive avatar research platform that I developed solely during my summer 2007 internship at Microsoft Research Asia [enter]
  • A video-based (note: not optical-based) motion capture camera and microphone array system (hardware and software) that I am currently building in collaboration with Yuxiao Hu (now with Microsoft, Redmond) et. al. for 3D audiovisual dynamic face data collection [enter]
  • Several emotional speech databases constructed for my research on emotional prosody and text-to-speech synthesis [enter]
  • A text messaging system with emotive audio-visual avatar that I developed jointly with Jilin Tu (now with GE) in a collaborative project between the UIUC IFP Group and the Motorola Multimedia Research Lab (MRL) [enter]
  • A personalized emotive audio-visual avatar constructed from a single 2D frontal-view face image on-the-fly that I developed in collabration with Yuxiao Hu [enter]
  • A POSER-based emotive audio-visual avatar that I developed in collabration with Jilin Tu [enter]
  • The fist text-driven emotive audio-visual avatar that I developed jointly with Jilin Tu based on the iFace 3D face modeling utility at UIUC [enter]
  • Diphone-based emotive text-to-speech synthesis based on the Festival-MBROLA architecture using an emotion transformer (transformaton of prosody & voice quality) [enter]
  • A synthesized speech example of the Corpus-Based Cantonese Text-to-Speech Synthesis System that I developed at iFlyTEK, China, 2002 ~ 2003 [download]
  • A synthesized speech example of the Corpus-Based Chinese-English Mixed-Lingual Text-to-Speech Synthesis System that I worked on at iFlyTEK, China, 2002 ~ 2003 [download]
  • A synthesized speech example of the KD-2000 Chinese Text-to-Speech System that I worked on at iFlyTEK, China, 2000 [download]