Detail publikace

Feature And Score Level Combination Of Subspace Gaussians In LVCSR Task

MOTLÍČEK, P. POVEY, D. KARAFIÁT, M.

Originální název

Feature And Score Level Combination Of Subspace Gaussians In LVCSR Task

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

Automatic Speech Recognition, Discriminativefeatures, System combination

Autoři

MOTLÍČEK, P.; POVEY, D.; KARAFIÁT, M.

Rok RIV

2013

Vydáno

27. 5. 2013

Nakladatel

IEEE Signal Processing Society

Místo

Vancouver

ISBN

978-1-4799-0355-9

Kniha

Proceedings of ICASSP 2013

Strany od

7604

Strany do

7608

Strany počet

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"
}