Performance of Czech Speech Recognition with Language Models Created from Public Resources

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F11%3A00185981" target="_blank" >RIV/68407700:21230/11:00185981 - isvavai.cz</a>

Alternative codes found

RIV/46747885:24220/11:#0001963

Result on the web

<a href="http://www.radioeng.cz" target="_blank" >http://www.radioeng.cz</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Performance of Czech Speech Recognition with Language Models Created from Public Resources

Original language description

In this paper, we investigate the usability of publicly available n-gram corpora for the creation of language models (LM) applicable for Czech speech recognition systems. N-gram LMs with various parameters and settings were created from two publicly available sets, Czech Web 1T 5-gram corpus provided by Google and 5-gram corpus created from the Czech National Corpus. We tested also a LM made of a large private resource of newspaper and broadcast texts collected by a Czech media mining company. The LMs were analyzed and compared via their perplexity rates and when employed in large vocabulary continuous speech recognition systems. Our study show that the Web1T-based LMs, even after intensive cleaning and normalization procedures, cannot compete with those made of smaller but more consistent corpora. The experiments done on large test data also illustrate the impact of Czech as highly inflective language on the perplexity, OOV, and recognition accuracy rates.

Czech name

—

Czech description

—

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

JA - Electronics and optoelectronics

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

2011

Confidentiality

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

Name of the periodical

Radioengineering

ISSN

1210-2512

e-ISSN

—

Volume of the periodical

40

Issue of the periodical within the volume

4

Country of publishing house

CZ - CZECH REPUBLIC

Number of pages

7

Pages from-to

1002-1008

UT code for WoS article

000298636800039

EID of the result in the Scopus database

—