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

Language

English

Original Abstract

Different neural net topologies for estimating features for speech recognition were presented. We introduced bottle-neck structure into previously proposed Split Context. This was done mainly to reduce size of resulting neural net, which serves as feature estimator. When bottle-neck outputs are used also as final outputs from neural network instead of probability estimates, the reduction of word error rate is also 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

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",
  note="presentation"
}