Speech Recognition in the Broadcast News Domain

Authors

DOI:

https://doi.org/10.18690/analipazu.1.1.54-56.2011

Keywords:

speech recognition, highly inflective language, language resources

Abstract

In this paper the structure of a speech recognition system is presented. We focus on Slovenian speech recognition.  UMB BN system is described. Currently, it is the most complex large vocabulary continuous speech recognition system for Slovenian language. It is designed for transcribing TV-news shows. In the paper language resources are also described being crucial in developing such systems.

Downloads

Download data is not yet available.

Author Biographies

  • Mirjam Sepesy Maučec, Faculty of Electrical Engineering, Computer Science and Informatics, University of Maribor / Smetanova 17, 2000 Maribor, Slovenia.

    Maribor, Slovenia. E-mail: mirjam.sepesy@um.si

  • Andrej Žgank , Faculty of Electrical Engineering, Computer Science and Informatics, University of Maribor / Smetanova 17, 2000 Maribor, Slovenia.

    Maribor, Slovenia. E-mail: andrej.zgank@uni-mb.si

Downloads

Published

03.05.2022

Issue

Vol. 1 No. 1 (2011): ANALI PAZU

Section

Prispevki

How to Cite

Sepesy Maučec, M., & Žgank , A. (2022). Speech Recognition in the Broadcast News Domain. Anali PAZU, 1(1), 54-56. https://doi.org/10.18690/analipazu.1.1.54-56.2011