Publication Details

Using MATLAB for Analysis of TRAP system

KARAFIÁT Martin and GRÉZL František. Using MATLAB for Analysis of TRAP system. Radioengineering, vol. 2003, no. 4, pp. 38-41. ISSN 1210-2512.
Czech title
Využití matlabu pro analýzu TRAP systému
Type
journal article
Language
english
Authors
Keywords

TRAP, speech recognition, features extraction, estimated probability analysis

Abstract

Using matlab for analysis of TRAP system. Especially, results from neural net classifiers. The utility of resulting figures is enhanced by the possibility of reading and displaying results from all critical bands at once. Resulting analyses are more focused on the reliability of classifiers than on the basic accuracy measure.

Annotation

This article describes a Matlab function for reading and processing file outputs from a structure of classifiers. These classifiers - neural nets - are used in speech recognition based on temporal trajectories (TRAP) of energy in frequency bands. This nonstandard approach is introduced and the program is presented. The utility of resulting figures is enhanced by the possibility of reading and displaying results from all critical bands at once. Resulting analyses are more focused on the reliability of classifiers than on the basic accuracy measure. The first uses colors and their depth to display both cues, reliability and accuracy, in one informative picture. Others are focused on more precise measures, where it is possible to precisely define classifier mistakes.

Published
2003
Pages
38-41
Journal
Radioengineering, vol. 2003, no. 4, ISSN 1210-2512
BibTeX
@ARTICLE{FITPUB7355,
   author = "Martin Karafi\'{a}t and Franti\v{s}ek Gr\'{e}zl",
   title = "Using MATLAB for Analysis of TRAP system",
   pages = "38--41",
   journal = "Radioengineering",
   volume = 2003,
   number = 4,
   year = 2003,
   ISSN = "1210-2512",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/7355"
}
Back to top