Academic Journals Database
Disseminating quality controlled scientific knowledge

Serbian Keyword Spotting System

ADD TO MY LIST
 
Author(s): Ljiljana Stanimirović | Milan D. Savić

Journal: Facta Universitatis Series : Electronics and Energetics
ISSN 0353-3670

Volume: 12;
Issue: 3;
Start page: 95;
Date: 1999;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Hidden Markov models | speech recongnition | man-machine dialogue

ABSTRACT
In this paper we present our recent work in implementing a keyword spotting system for detecting a limited number of keywords in continuous speech of Serbian. The keywords are detecting without modeling the non-keyword parts of the sentence using confidence measure and HMMs (Hidden Markov Models). Only keywords have to be model by HMMs in the way which we propose in this paper, that each syllable is three-state HMM. In this paper we also introduce MSQ - measure of system's quality in order to determine optimal step and optimal threshold for the confidence measure in the decoding phase. The obtained results show that proposed procedure can be used in interactive man-machine dialogue services.
Affiliate Program      Why do you need a reservation system?