To estimate the parameters of stochastic knowledge bases for a speech understanding system, many utterances spoken by many people have to be examined. For the regarded domain of a 'graphic editor', two different manners of collecting training data are discussed. An analysis of spoken commands recorded by a 'Wizard of Oz'-simulation shows that the way to talk to a computer usually depends on how familiar a subject is with a computer. Keywords: speech understanding, training of stochastic models, 'Wizard of Oz'-simulation
Cite as: Müller, J., Stahl, H. (1995) Collecting and analyzing spoken utterances for a speech controlled application. Proc. 4th European Conference on Speech Communication and Technology (Eurospeech 1995), 1437-1440, doi: 10.21437/Eurospeech.1995-322
@inproceedings{muller95_eurospeech,
author={Johannes Müller and Holger Stahl},
title={{Collecting and analyzing spoken utterances for a speech controlled application}},
year=1995,
booktitle={Proc. 4th European Conference on Speech Communication and Technology (Eurospeech 1995)},
pages={1437--1440},
doi={10.21437/Eurospeech.1995-322}
}