Detail publikačního výsledku

A Symmetrization of the Subspace Gaussian Mixture Model

POVEY, D.; KARAFIÁT, M.; GHOSHAL, A.; SCHWARZ, P.

Originální název

A Symmetrization of the Subspace Gaussian Mixture Model

Anglický název

A Symmetrization of the Subspace Gaussian Mixture Model

Druh

Stať ve sborníku mimo WoS a Scopus

Originální abstrakt

We have described a modification to the Subspace Gaussian Mixture Model which we call the Symmetric SGMM. This is a very natural extension which removes an asymmetry in the way the Gaussian mixture weights were previously computed. The extra computation is minimal but the memory used for the acoustic model is nearly doubled. Our experimental results were inconsistent: on one setup we got a large improvement of 1.5% absolute, and on another setup it was much smaller.

Anglický abstrakt

We have described a modification to the Subspace Gaussian Mixture Model which we call the Symmetric SGMM. This is a very natural extension which removes an asymmetry in the way the Gaussian mixture weights were previously computed. The extra computation is minimal but the memory used for the acoustic model is nearly doubled. Our experimental results were inconsistent: on one setup we got a large improvement of 1.5% absolute, and on another setup it was much smaller.

Klíčová slova

Speech Recognition, Hidden Markov Models, Subspace Gaussian Mixture Models

Klíčová slova v angličtině

Speech Recognition, Hidden Markov Models, Subspace Gaussian Mixture Models

Autoři

POVEY, D.; KARAFIÁT, M.; GHOSHAL, A.; SCHWARZ, P.

Rok RIV

2012

Vydáno

22.05.2011

Nakladatel

IEEE Signal Processing Society

Místo

Praha

ISBN

978-1-4577-0537-3

Kniha

Proceedings of 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing

Strany od

4504

Strany do

4507

Strany počet

4

URL

BibTex

@inproceedings{BUT76375,
  author="Daniel {Povey} and Martin {Karafiát} and Arnab {Ghoshal} and Petr {Schwarz}",
  title="A Symmetrization of the Subspace Gaussian Mixture Model",
  booktitle="Proceedings of 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing",
  year="2011",
  pages="4504--4507",
  publisher="IEEE Signal Processing Society",
  address="Praha",
  isbn="978-1-4577-0537-3",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2011/povey_icassp2011_4504.pdf"
}