Publication detail

Neural network topologies and bottle neck features in speech recognition

GRÉZL, F. KARAFIÁT, M. ČERNOCKÝ, J.

Original Title

Neural network topologies and bottle neck features in speech recognition

Type

presentation, poster

Language

English

Original Abstract

Different neural net topologies for estimating features for speechrecognition were presented. We introduced bottle-neck structure intopreviously proposed Split Context. This was done mainly to reduce sizeof resulting neural net, which serves as feature estimator. Whenbottle-neck outputs are used also as final outputs from neural networkinstead of probability estimates, the reduction of word error rate isalso reached.

Keywords

neural networks, topologies, speech recognition, bottle-neck features

Authors

GRÉZL, F.; KARAFIÁT, M.; ČERNOCKÝ, J.

Released

28. 6. 2007

Location

Brno

Pages from

78

Pages to

82

Pages count

5

URL

http://www.fit.vutbr.cz/~grezl/publi/mlmi2007.pdf

BibTex

@misc{BUT63689,
  author="František {Grézl} and Martin {Karafiát} and Jan {Černocký}",
  title="Neural network topologies and bottle neck features in speech recognition",
  year="2007",
  pages="78--82",
  address="Brno",
  url="http://www.fit.vutbr.cz/~grezl/publi/mlmi2007.pdf",
  note="presentation, poster"
}