Thomas Hain

Professor of Speech and Audio Technology

Machine Intelligence for Natural Interfaces
Speech and Hearing Research Group
Department of Computer Science

Current funded projects
  • Natural Speech Technology
  • DocuMeet
  • SLatr
  • Language learning for Dutch Speakers of English
Current further activities
Current PhD Projects
If you are interested in a PhD, have a look at the topics page.
  • Arabic Speech Recognition
  • Content linking for audio-visual lecture recordings
  • Canonical acoustic models
  • Environment models
  • Rich diarisation for media archives
  • The use of context in speaker identification
  • Longitudinal adapatation in health applications
  • Phase information in speech and hearing
Past Projects
  • Domain adaptation for LVCSR
  • AMI
  • U-STAR