Detail publikace

Feature Gaussianization for Speech Recognition

MATĚJKA, P., ČERNOCKÝ, J.

Originální název

Feature Gaussianization for Speech Recognition

Anglický název

Feature Gaussianization for Speech Recognition

Jazyk

en

Originální 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.

Anglický 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.

Dokumenty

BibTex


@inproceedings{BUT5411,
  author="Pavel {Matějka} and Jan {Černocký}",
  title="Feature Gaussianization for Speech Recognition",
  annote="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.",
  address="Slovak University of Technology in Bratislava",
  booktitle="Conference Proceedings",
  chapter="5411",
  institution="Slovak University of Technology in Bratislava",
  year="2002",
  month="may",
  pages="93",
  publisher="Slovak University of Technology in Bratislava",
  type="conference paper"
}