Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Statistical Models of Text in Continuous Speech Recognition

Statistical Models of Text in Continuous Speech Recognition A major difficulty in continuous speech recognition research is the lack of effective and objective evaluation of the statistical models of text. Herbert Simon's view for evaluating theories is here applied to the statistical modelling of text. Three significant contributions can be identified. First, a timeseries representation of text is used to identify three wellknown empirical laws of text generation. These laws provide an effective and objective approach for evaluating four leading statistical models of text. Second, it is shown that the SimonYule model of text provides a constructive mechanism for those laws. Third, based on Simon's explanatory processes of imitation and association, an adaptive framework for continuous speech recognition is suggested. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Kybernetes Emerald Publishing

Statistical Models of Text in Continuous Speech Recognition

Kybernetes , Volume 20 (5): 12 – May 1, 1991

Loading next page...
 
/lp/emerald-publishing/statistical-models-of-text-in-continuous-speech-recognition-w2YO2397WG

References (24)

Publisher
Emerald Publishing
Copyright
Copyright © Emerald Group Publishing Limited
ISSN
0368-492X
DOI
10.1108/eb005896
Publisher site
See Article on Publisher Site

Abstract

A major difficulty in continuous speech recognition research is the lack of effective and objective evaluation of the statistical models of text. Herbert Simon's view for evaluating theories is here applied to the statistical modelling of text. Three significant contributions can be identified. First, a timeseries representation of text is used to identify three wellknown empirical laws of text generation. These laws provide an effective and objective approach for evaluating four leading statistical models of text. Second, it is shown that the SimonYule model of text provides a constructive mechanism for those laws. Third, based on Simon's explanatory processes of imitation and association, an adaptive framework for continuous speech recognition is suggested.

Journal

KybernetesEmerald Publishing

Published: May 1, 1991

There are no references for this article.