Publication detail

Data adaptation for Hidden Markov Model in speech recognition

MATĚJKA, P., SIGMUND, M., ČERNOCKÝ, J.

Original Title

Data adaptation for Hidden Markov Model in speech recognition

Type

conference paper

Language

English

Original Abstract

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.

Key words in English

speaker speach recognition gaussianization

Authors

MATĚJKA, P., SIGMUND, M., ČERNOCKÝ, J.

RIV year

2002

Released

25. 4. 2002

Location

Brno

ISBN

80-214-2116-9

Book

Proceedings of 8th Conference STUDENT EEICT 2002

Edition number

1

Pages from

317

Pages to

320

Pages count

4

BibTex

@inproceedings{BUT5410,
  author="Pavel {Matějka} and Milan {Sigmund} and Jan {Černocký}",
  title="Data adaptation for Hidden Markov Model in speech recognition",
  booktitle="Proceedings of 8th Conference STUDENT EEICT 2002",
  year="2002",
  number="1",
  pages="4",
  address="Brno",
  isbn="80-214-2116-9"
}