Detail publikace

The Role of Neural Network Size in TRAP/HATS Feature Extraction

GRÉZL, F.

Originální název

The Role of Neural Network Size in TRAP/HATS Feature Extraction

Anglický název

The Role of Neural Network Size in TRAP/HATS Feature Extraction

Jazyk

en

Originální abstrakt

This article examines the performance of TRAP/HATS based probabilistic features in ASR. The sizes of neural networks in both stages of processing are changed and the influence is evaluated.

Anglický abstrakt

This article examines the performance of TRAP/HATS based probabilistic features in ASR. The sizes of neural networks in both stages of processing are changed and the influence is evaluated.

Dokumenty

BibTex


@inproceedings{BUT76446,
  author="František {Grézl}",
  title="The Role of Neural Network Size in TRAP/HATS Feature Extraction",
  annote="This article examines the performance of TRAP/HATS based probabilistic features
in ASR. The sizes of neural networks in both stages of processing are changed and
the influence is evaluated.",
  address="Springer Verlag",
  booktitle="Proceedings Text, Speech and Dialogue 2011",
  chapter="76446",
  edition="LNAI 6836",
  howpublished="print",
  institution="Springer Verlag",
  number="9",
  year="2011",
  month="september",
  pages="315--322",
  publisher="Springer Verlag",
  type="conference paper"
}