Neural network based language models for highly inflective languages

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F09%3APU82680" target="_blank" >RIV/00216305:26230/09:PU82680 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Neural network based language models for highly inflective languages

Original language description

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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

JC - Computer hardware and software

OECD FORD branch

—

Project

Result was created during the realization of more than one project. More information in the Projects tab.

Continuities

Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

2009

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proc. ICASSP 2009

ISBN

978-1-4244-2354-5

ISSN

—

e-ISSN

—

Number of pages

4

Pages from-to

—

Publisher name

IEEE Signal Processing Society

Place of publication

Taipei

Event location

Taipei

Event date

Apr 19, 2009

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—