Detail publikace

Neural network topologies and bottle neck features in speech recognition

GRÉZL, F. KARAFIÁT, M. ČERNOCKÝ, J.

Originální název

Neural network topologies and bottle neck features in speech recognition

Typ

audiovizuální tvorba

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

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

Autoři

GRÉZL, F.; KARAFIÁT, M.; ČERNOCKÝ, J.

Vydáno

28. 6. 2007

Místo

Brno

Strany od

78

Strany do

82

Strany počet

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"
}