Publication detail

Variational Approximation of Long-span Language Models for LVCSR

DEORAS, A. MIKOLOV, T. KOMBRINK, S. KARAFIÁT, M. KHUDANPUR, S.

Original Title

Variational Approximation of Long-span Language Models for LVCSR

Type

article in a collection out of WoS and Scopus

Language

English

Original Abstract

We have presented experimental evidence that (n-gram) variational approximations of long-span LMs yield greater accuracy in LVCSR than standard n-gram models estimated from the same training text.

Keywords

Recurrent Neural Network, Language Model, Variational Inference

Authors

DEORAS, A.; MIKOLOV, T.; KOMBRINK, S.; KARAFIÁT, M.; KHUDANPUR, S.

RIV year

2011

Released

22. 5. 2011

Publisher

IEEE Signal Processing Society

Location

Praha

ISBN

978-1-4577-0537-3

Book

Proceedings of the 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011

Pages from

5532

Pages to

5535

Pages count

4

URL

http://www.fit.vutbr.cz/research/groups/speech/publi/2011/deoras_icassp2011_5532.pdf

BibTex

@inproceedings{BUT76377,
  author="Anoop {Deoras} and Tomáš {Mikolov} and Stefan {Kombrink} and Martin {Karafiát} and Sanjeev {Khudanpur}",
  title="Variational Approximation of Long-span Language Models for LVCSR",
  booktitle="Proceedings of the 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011",
  year="2011",
  pages="5532--5535",
  publisher="IEEE Signal Processing Society",
  address="Praha",
  isbn="978-1-4577-0537-3",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2011/deoras_icassp2011_5532.pdf"
}