Detail publikace

Combination of Speech Features Using Smoothed Heteroscedastic Linear Discriminant Analysis

BURGET, L.

Originální název

Combination of Speech Features Using Smoothed Heteroscedastic Linear Discriminant Analysis

Anglický název

Combination of Speech Features Using Smoothed Heteroscedastic Linear Discriminant Analysis

Jazyk

en

Originální abstrakt

Feature combination techniques based on PCA, LDA and HLDA are compared in experiments where limited amount of training data is available. Success with feature combination can be quite dependent on proper estimation of statistics required by the used technique. Insufficiency of training data is, therefore, an important problem, which has to be taken in to account in our experiments.
Besides of some standard approaches increasing robustness of statistic estimation, methods based on combination of LDA and HLDA are proposed. An improved recognition performance obtained using these methods is demonstrated in experiments.

Anglický abstrakt

Feature combination techniques based on PCA, LDA and HLDA are compared in experiments where limited amount of training data is available. Success with feature combination can be quite dependent on proper estimation of statistics required by the used technique. Insufficiency of training data is, therefore, an important problem, which has to be taken in to account in our experiments.
Besides of some standard approaches increasing robustness of statistic estimation, methods based on combination of LDA and HLDA are proposed. An improved recognition performance obtained using these methods is demonstrated in experiments.

Dokumenty

BibTex


@inproceedings{BUT17132,
  author="Lukáš {Burget}",
  title="Combination of Speech Features Using Smoothed Heteroscedastic Linear Discriminant Analysis",
  annote="Feature combination techniques based on PCA, LDA and HLDA are compared in experiments where limited amount of training data is available. Success with feature combination can be quite dependent on proper estimation of statistics required by the used technique. Insufficiency of training data is, therefore, an important problem, which has to be taken in to account in our experiments.
Besides of some standard approaches increasing robustness of statistic estimation, methods based on combination of LDA and HLDA are proposed. An improved recognition performance obtained using these methods is demonstrated in experiments.", address="Sunjin Printing Co,", booktitle="Proc. 8th International Conference on Spoken Language Processing", chapter="17132", institution="Sunjin Printing Co,", year="2004", month="june", pages="2549--2552", publisher="Sunjin Printing Co,", type="conference paper" }