Authors: Popović, Branislav
Janev, Marko 
Delić, Vlado
Affiliations: Mathematical Institute of the Serbian Academy of Sciences and Arts 
Title: Gaussian selection algorithm in Continuous Speech Recognition
Journal: 2012 20th Telecommunications Forum, TELFOR 2012 - Proceedings
First page: 705
Last page: 712
Conference: 20th Telecommunications Forum, TELFOR 2012; Belgrade; Serbia; 20 November 2012 through 22 November 2012
Issue Date: 1-Dec-2012
ISBN: 978-1-467-32984-2
DOI: 10.1109/TELFOR.2012.6419307
Clustering of Gaussian mixture components, i.e. Hierarchical Gaussian mixture model clustering (HGMMC) is a key component of Gaussian selection (GS) algorithm, used in order to increase the speed of a Continuous Speech Recognition (CSR) system, without any significant degradation of its recognition accuracy. In this paper a novel Split-and-Merge (S&M) HGMMC algorithm is applied to GS, in order to achieve a better trade-off between speed and accuracy in a CSR task. The algorithm is further improved by introducing model selection in order to obtain the best possible trade-off between recognition accuracy and computational load in a GS task applied within an actual recognition system. At the end of the paper we discuss additional improvements towards finding the optimal setting for the Gaussian selection scheme.
Keywords: continuous speech recognition | Gaussian selection | hierarchical clustering | split-and-merge
Publisher: IEEE

Show full item record

Page view(s)

checked on May 9, 2024

Google ScholarTM




Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.