Článek ve sborníku konference | |
| Matějka, P., Černocký, J.: Feature gaussianization in speech recognition, In: Proc. 12th International scientific conference Radioelektronika 2002, Bratislava, SK, STUBA, 2002, s. 4, ISBN 80-227-1700-2 | | Jazyk publikace: | angličtina |
|---|
| Název publikace: | Feature gaussianization in speech recognition |
|---|
| Název (cs): | Gaussianizace dat v rozpoznávání řeči |
|---|
| Strany: | 4 |
|---|
| Sborník: | Proc. 12th International scientific conference Radioelektronika 2002 |
|---|
| Konference: | 12th International Czech-Slovak Scientific conference Radioelektronika 2002 |
|---|
| Místo vydání: | Bratislava, SK |
|---|
| Rok: | 2002 |
|---|
| ISBN: | 80-227-1700-2 |
|---|
| Vydavatel: | Slovenská technická univerzita v Bratislavě |
|---|
| URL: | http://www.fit.vutbr.cz/~matejkap/publi/2002/RA2002.pdf [PDF] |
|---|
| Klíčová slova |
|---|
| rozpoznávání řeči,Gaussianization |
| Anotace |
|---|
| Gaussianizace dat v rozpoznávání řeči |
| Abstrakt |
|---|
| In Hidden Markov models, speech data are modeled by Gaussian
distributions. In this paper, we propose to Gaussianize the features to
better fit to this modeling. A distribution of the data is estimated
and a transform function is derived. We test three methods of the
transform estimation (global, speaker based, frame based) and report
results on the SPINE 2000 task with SPhinx recognizer. We conclude that
the proposed method is a cheap way to increase the recognition accuracy. |
| BibTeX: |
|---|
@INPROCEEDINGS{
author = {Pavel Matějka and Jan Černocký},
title = {Feature gaussianization in speech recognition},
pages = {4},
booktitle = {Proc. 12th International scientific conference
Radioelektronika 2002},
year = {2002},
location = {Bratislava, SK},
publisher = {Slovak University of Technology in Bratislava},
ISBN = {80-227-1700-2},
language = {english},
url = {http://www.fit.vutbr.cz/research/view_pub.php?id=7082}
} |
|