Product Details
AMI Large vocabulary continuous speech recognizer
Created: 2005
Czech title
AMI Rozpoznávač spojité řeči s velkým slovníkem
Type
software
License
required - licence fee
Authors
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Hain Thomas (USF)
Karafiát Martin, Ing., Ph.D. (DCGM FIT BUT)
Hain Thomas (USF)
Karafiát Martin, Ing., Ph.D. (DCGM FIT BUT)
Keywords
speech processing
Description
The AMI speech recognition system is being developed in cooperation of partners of EU-sponsored project AMI: University of Sheffield, IDIAP, University of Edinburgh, BUT and TNO Netherlands. It is based on Hidden Markov models. Brno group has contributed novel methods of acoustic modeling (discriminative training and linear transforms) to the recognizer. The system was successfully tested in NIST Meeting Transcription Evaluations in 2005.
Projects
Augmented Multi-party Interaction (506811-AMI)
Multi Modal Meeting Manager (IST-2001-34485)
New trends in research and application of voice technology (GA102/05/0278)
Multi Modal Meeting Manager (IST-2001-34485)
New trends in research and application of voice technology (GA102/05/0278)
Research groups
Speech Data Mining Research Group BUT Speech@FIT (VZ SPEECH)
Departments