Conference paper

MIKOLOV Tomáš, KOPECKÝ Jiří, BURGET Lukáš, GLEMBEK Ondřej and ČERNOCKÝ Jan. Neural network based language models for highly inflective languages. In: Proc. ICASSP 2009. Taipei: IEEE Signal Processing Society, 2009, p. 4. ISBN 978-1-4244-2354-5.
Publication language:english
Original title:Neural network based language models for highly inflective languages
Title (cs):Jazykové modely založené na neuronových sítích pro vysoce ohebné jazyky
Proceedings:Proc. ICASSP 2009
Conference:International Conference on Acoustics, Speech, and Signal Processing
Place:Taipei, TW
Publisher:IEEE Signal Processing Society
language modeling, neural networks, inflective languages
The paper is on neural network based language models for highly inflective languages
Speech recognition of inflectional and morphologically rich languages like Czech is currently quite a challenging task, because simple n-gram techniques are unable to capture important regularities in the data. Several possible solutions were proposed, namely class based models, factored models, decision trees and neural networks. This paper describes improvements obtained in recognition of spoken Czech lectures using languagemodels based on neural networks. Relative reductions in word error rate are more than 15% over baseline obtained with adapted 4-gram backoff language model using modified Kneser-Ney smoothing.
   author = {Tom{\'{a}}{\v{s}} Mikolov and Ji{\v{r}}{\'{i}} Kopeck{\'{y}}
	and Luk{\'{a}}{\v{s}} Burget and Ond{\v{r}}ej Glembek and
	Jan {\v{C}}ernock{\'{y}}},
   title = {Neural network based language models for highly inflective
   pages = {4},
   booktitle = {Proc. ICASSP 2009},
   year = {2009},
   location = {Taipei, TW},
   publisher = {IEEE Signal Processing Society},
   ISBN = {978-1-4244-2354-5},
   language = {english},
   url = {}

Your IPv4 address:
Switch to IPv6 connection

DNSSEC [dnssec]