Detail aplikovaného výsledku

AMI Large vocabulary continuous speech recognizer

HAIN, T.; BURGET, L.; KARAFIÁT, M.

Originální název

AMI Large vocabulary continuous speech recognizer

Anglický název

AMI Large vocabulary continuous speech recognizer

Druh

Software

Abstrakt

The AMI speech recognition system is being developed in cooperation ofpartners of EU-sponsored project AMI: University of Sheffield, IDIAP,University of Edinburgh, BUT and TNO Netherlands. It is based on HiddenMarkov models. Brno group has contributed novel methods of acousticmodeling (discriminative training and linear transforms) to therecognizer. The system was successfully tested in NIST MeetingTranscription Evaluations in 2005.

Abstrakt aglicky

The AMI speech recognition system is being developed in cooperation ofpartners of EU-sponsored project AMI: University of Sheffield, IDIAP,University of Edinburgh, BUT and TNO Netherlands. It is based on HiddenMarkov models. Brno group has contributed novel methods of acousticmodeling (discriminative training and linear transforms) to therecognizer. The system was successfully tested in NIST MeetingTranscription Evaluations in 2005.

Klíčová slova

speech processing

Klíčová slova anglicky

speech processing

Umístění

https://www.fit.vut.cz/research/product/25/

Licenční poplatek

K využití výsledku jiným subjektem je vždy nutné nabytí licence

www

https://www.fit.vut.cz/research/product/25/