Language models for spontaneous speech recognition

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F15%3A00230233" target="_blank" >RIV/68407700:21230/15:00230233 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Language models for spontaneous speech recognition
Original language description
The paper presents the creation of n-gram Language Models (LMs) for the purposes of spontaneous speech recognition with the special focus on the recognition performed with the data from the Nijmegen Corpus of Casual Czech (NCCCz). Required LMs which cover spontaneous or casual speech re- spectively were created using the data available in the col- lected corpus NCCCz. These models were combined with a general model built on the basis Czech National Corpus. The creation of LMs, their adaptation to specific thematic do- main (casual speech) were created using SRILM toolkit. The quality of created LMs was measured on the basis Perplex- ity and Out-Of-Vocabulary words at the text level, same as they was used within the automatic speech recognition and theachieved Word Error Rates are also presented. The study shows that created LMs were suitable for given purpose and achieved results were related to other works presenting the spontaneous speech recognition.
Czech name
—
Czech description
—

Publication year
2015
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the 19th International Scientific Student Conferenece POSTER 2015
ISBN
978-80-01-05499-4
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
1-4
Publisher name
Czech Technical University in Prague
Place of publication
Praha
Event location
Praha
Event date
May 14, 2015
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—

Similar results(10)