---+ Speech Research Group The Speech Research Group is part of [[http://mi.eng.cam.ac.uk/][the Machine Intelligence Laboratory]]. Its mission is to advance our knowledge of computer-based spoken language processing and develop effective algorithms for implementing applications. Its primary specialism is in [[http://htk.eng.cam.ac.uk/docs/cuhtk.shtml][ large vocabulary speech transcription]] and related technologies. It also has active research interests in [[http://mi.eng.cam.ac.uk/research/dialogue/][spoken dialogue systems]], multimedia document retrieval, [[http://divf.eng.cam.ac.uk/smt/][statistical machine translation]], speech synthesis and machine learning. ---++ Research Areas The research topic areas covered by the Speech Research Group include: * acoustic modelling using statistical models * basic research in machine learning * [[http://mi.eng.cam.ac.uk/research/dialogue][dialogue optimisation using reinforcement learning]] * large vocabulary recognition * multimedia document retrieval * portability in speech recognition * speaker and environment adaptation * [[http://mi.eng.cam.ac.uk/research/dialogue/][spoken dialogue systems and !VoiceXML]] * statistical language modelling * [[http://divf.eng.cam.ac.uk/smt/][statistical machine translation]] * transcription of found speech For a simple introduction to speech recognition click [[http://www-g.eng.cam.ac.uk/125/now/speech.html][here]]. ---++ Other Things We Do * The [[http://htk.eng.cam.ac.uk/][HTK HMM Toolkit]] is developed and maintained by the [[Main/Speech.WebHome][Speech Research Group]].
This topic: Main/Speech/SeminarVideos
>
WebHome
Topic revision: revision 1 (raw view)
No permission to view
System.WebBottomBarExample