Detail publikace

Recurrent Neural Network based Language Modeling in Meeting Recognition

Originální název

Recurrent Neural Network based Language Modeling in Meeting Recognition

Anglický název

Recurrent Neural Network based Language Modeling in Meeting Recognition

Jazyk

en

Originální abstrakt

In this paper we recommend the use of RNN language models as easy mean to improve an existing LVCSR system, either by improving ngram models using data sampled from an RNN or by performing the proposed rescoring and adaptation postprocessing steps.

Anglický abstrakt

In this paper we recommend the use of RNN language models as easy mean to improve an existing LVCSR system, either by improving ngram models using data sampled from an RNN or by performing the proposed rescoring and adaptation postprocessing steps.

BibTex


@inproceedings{BUT76441,
  author="Stefan {Kombrink} and Tomáš {Mikolov} and Martin {Karafiát} and Lukáš {Burget}",
  title="Recurrent Neural Network based Language Modeling in Meeting Recognition",
  annote="In this paper we recommend the use of RNN language models as easy mean to improve
an existing LVCSR system, either by improving ngram models using data sampled
from an RNN or by performing the proposed rescoring and adaptation postprocessing
steps.",
  address="International Speech Communication Association",
  booktitle="Proceedings of Interspeech 2011",
  chapter="76441",
  edition="NEUVEDEN",
  howpublished="print",
  institution="International Speech Communication Association",
  number="8",
  year="2011",
  month="august",
  pages="2877--2880",
  publisher="International Speech Communication Association",
  type="conference paper"
}