Detail publikace
Some like it Gaussian...
MATĚJKA, P., SCHWARZ, P., KARAFIÁT, M., ČERNOCKÝ, J.
Originální název
Some like it Gaussian...
Anglický název
Some like it Gaussian...
Jazyk
en
Originální abstrakt
In Hidden Markov models, speech features 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 have tested two methods of the transform estimation (global and speaker based). The results are reported on recognition of isolated Czech words (SpeechDat-E) with CI and CD models and on medium vocabulary continuous speech recognition task (SPINE). Gaussianized data provided in all three cases results superior to standard MFC coefficients proving, that the gaussianization is a cheap way to increase the recognition accuracy
Anglický abstrakt
In Hidden Markov models, speech features 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 have tested two methods of the transform estimation (global and speaker based). The results are reported on recognition of isolated Czech words (SpeechDat-E) with CI and CD models and on medium vocabulary continuous speech recognition task (SPINE). Gaussianized data provided in all three cases results superior to standard MFC coefficients proving, that the gaussianization is a cheap way to increase the recognition accuracy
Dokumenty
BibTex
@inproceedings{BUT10260,
author="Pavel {Matějka} and Petr {Schwarz} and Martin {Karafiát} and Jan {Černocký}",
title="Some like it Gaussian...",
annote="In Hidden Markov models, speech features 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 have tested two methods of the transform
estimation (global and speaker based). The results are reported on
recognition of isolated Czech words (SpeechDat-E) with
CI and CD models and on medium vocabulary continuous speech
recognition task (SPINE). Gaussianized data provided in all three
cases results superior to standard MFC coefficients proving, that the
gaussianization is a cheap way to increase the recognition accuracy",
address="Springer Verlag",
booktitle="Proc. 5th International Conference Text, Speech and Dialogue, TSD2002",
chapter="10260",
edition="Lecture notes in artificial intelligence 2448",
institution="Springer Verlag",
year="2002",
month="september",
pages="321--324",
publisher="Springer Verlag",
type="conference paper"
}