DMCA
Computations and Evaluations of an Optimal Feature-set for an HMM-based Recognizer (1996)
| Citations: | 4 - 1 self |
BibTeX
@TECHREPORT{Mashao96computationsand,
author = {Daniel Johannes Mashao},
title = {Computations and Evaluations of an Optimal Feature-set for an HMM-based Recognizer},
institution = {},
year = {1996}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
The benefits of a speech recognition machine would be many, resulting in the improvement of the quality of life for people. The design of a speech recognition system can be divided into two parts, commonly known as the front-end and back-end. The front-end deals with the conversion of the analog speech signal into features for classification. This thesis investigates optimal feature-sets for speech recognition. The objectives for an optimal feature-set are improved recognition performance, noise robustness, talker insensitivity and efficiency. Three problems that make it difficult to find optimal features are: 1) the amount of resources (time and computations) required to evaluate the performance of a feature-set, 2) the size of the feature space, and 3) the dependence of features upon some words in t...
