Speech Technology group

Speech processing has been a research area for more than 60 years. The ultimate goal has been, and still is, to make machines understand and produce speech as a naturally and easily as humans.

Using speech for communications is natural for humans. Thus, a logical goal is to use speech also as an interface between humans and machines instead of keyboards, mouse, touch-sensitive screens etc. In addition to improving the usability of the interface for people in general, speech based interfaces would dramatically improve the quality of life for many groups of persons disabled with respect to e.g. movements, sight, hearing and talking.

• Automatic speech recognition
  • Utterance verification
  • Multilingual speech recognition
  • Robust speech recognition
  • Distributed speech recognition
• Speech synthesis
• Unit selection synthesis
• HMM synthesis
• Speech based human machine dialogue systems
• Speech database development





Research projects BRAGE FONEMA VOCALS

People in the Speech Techology Group




Updated: 2006-02-01