Přístupnostní navigace
E-application
Search Search Close
Publication detail
MATĚJKA, P., SCHWARZ, P., KARAFIÁT, M., ČERNOCKÝ, J.
Original Title
Some like it Gaussian...
Type
conference paper
Language
English
Original Abstract
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
Keywords
speech recognition, feature extraction, Gaussianization, non-linear transform
Authors
RIV year
2002
Released
30. 9. 2002
Publisher
Springer Verlag
Location
Berlin
ISBN
3-540-44129-8
Book
Proc. 5th International Conference Text, Speech and Dialogue, TSD2002
Edition
Lecture notes in artificial intelligence 2448
Pages from
321
Pages to
324
Pages count
4
URL
http://www.fit.vutbr.cz/~matejkap/publi/2002/tsd2002.pdf
BibTex
@inproceedings{BUT10260, author="Pavel {Matějka} and Petr {Schwarz} and Martin {Karafiát} and Jan {Černocký}", title="Some like it Gaussian...", booktitle="Proc. 5th International Conference Text, Speech and Dialogue, TSD2002", year="2002", series="Lecture notes in artificial intelligence 2448", pages="321--324", publisher="Springer Verlag", address="Berlin", isbn="3-540-44129-8", url="http://www.fit.vutbr.cz/~matejkap/publi/2002/tsd2002.pdf" }