Detail publikace

Hierarchical Neural Net Architectures for Feature Extraction in ASR

Originální název

Hierarchical Neural Net Architectures for Feature Extraction in ASR

Anglický název

Hierarchical Neural Net Architectures for Feature Extraction in ASR

Jazyk

en

Originální abstrakt

The paper is on the incorporation of Bottle-Neck features into hierarchical architecture of classifiers. This architecture was used for feature extraction for LVCSR of meetings and the resulting features were evaluated on NIST RT'05 and RT'07 test sets.

Anglický abstrakt

The paper is on the incorporation of Bottle-Neck features into hierarchical architecture of classifiers. This architecture was used for feature extraction for LVCSR of meetings and the resulting features were evaluated on NIST RT'05 and RT'07 test sets.

BibTex


@inproceedings{BUT35026,
  author="František {Grézl} and Martin {Karafiát}",
  title="Hierarchical Neural Net Architectures for Feature Extraction in ASR",
  annote="The paper is on the incorporation of Bottle-Neck features into hierarchical
architecture of classifiers. This architecture was used for feature extraction
for LVCSR of meetings and the resulting features were evaluated on NIST RT'05 and
RT'07 test sets.",
  address="International Speech Communication Association",
  booktitle="Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010)",
  chapter="35026",
  edition="NEUVEDEN",
  howpublished="print",
  institution="International Speech Communication Association",
  journal="Proceedings of Interspeech",
  number="9",
  year="2010",
  month="september",
  pages="1201--1204",
  publisher="International Speech Communication Association",
  type="conference paper"
}