Publication detail

Feature And Score Level Combination Of Subspace Gaussians In LVCSR Task

MOTLÍČEK, P. POVEY, D. KARAFIÁT, M.

Original Title

Feature And Score Level Combination Of Subspace Gaussians In LVCSR Task

Type

article in a collection out of WoS and Scopus

Language

English

Original Abstract

We have demonstrated that the SGMM framework is an efficient approachin the LVCSR task. Overall evaluations of SGMMs exploitingpowerful but complex PLP-BN features yield similar results asthose obtained by conventional HMM/GMMs. Nevertheless, the totalnumber of SGMM parameters is about 3 times less than in theHMM/GMM framework. Evaluation results also indicate differentproperties of the examined acoustic modeling techniques. AlthoughSGMMs consistently outperform HMM/GMMs when built over individualfeatures, HMM/GMMs can benefit much more from thefeature-level combination than SGMMs. Nevertheless based on ananalysis measuring complementarity of individual recognition systems,we show that SGMM-based recognizers produce heterogeneousoutputs (scores) and thus subsequent score-level combinationcan bring additional improvement.

Keywords

Automatic Speech Recognition, Discriminativefeatures, System combination

Authors

MOTLÍČEK, P.; POVEY, D.; KARAFIÁT, M.

RIV year

2013

Released

27. 5. 2013

Publisher

IEEE Signal Processing Society

Location

Vancouver

ISBN

978-1-4799-0355-9

Book

Proceedings of ICASSP 2013

Pages from

7604

Pages to

7608

Pages count

5

URL

http://www.fit.vutbr.cz/research/groups/speech/publi/2013/motlicek_icassp2013_0007604.pdf

BibTex

@inproceedings{BUT103519,
  author="Petr {Motlíček} and Daniel {Povey} and Martin {Karafiát}",
  title="Feature And Score Level Combination Of Subspace Gaussians In LVCSR Task",
  booktitle="Proceedings of ICASSP 2013",
  year="2013",
  pages="7604--7608",
  publisher="IEEE Signal Processing Society",
  address="Vancouver",
  isbn="978-1-4799-0355-9",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2013/motlicek_icassp2013_0007604.pdf"
}