DocumentCode
3522834
Title
Some statistical issues in the comparison of speech recognition algorithms
Author
Gillick, L. ; Cox, S.J.
Author_Institution
Dragon Syst. Inc., Newton, MA, USA
fYear
1989
fDate
23-26 May 1989
Firstpage
532
Abstract
The authors present two simple tests for deciding whether the difference in error rates between two algorithms tested on the same data set is statistically significant. The first (McNemar´s test) requires the errors made by an algorithm to be independent events and is found to be most appropriate for isolated-word algorithms. The second (a matched-pairs test) can be used even when errors are not independent events and is more appropriate for connected speech
Keywords
error statistics; speech recognition; data set; error rates; isolated-word algorithms; matched-pairs test; speech recognition algorithms; statistics; Bridges; Contracts; Laboratories; Maximum likelihood estimation; Parameter estimation; Random variables; Speech recognition; Telecommunications; Testing; Uncertainty;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech, and Signal Processing, 1989. ICASSP-89., 1989 International Conference on
Conference_Location
Glasgow
ISSN
1520-6149
Type
conf
DOI
10.1109/ICASSP.1989.266481
Filename
266481
Link To Document