Please use this identifier to cite or link to this item: http://dspace.unimap.edu.my:80/xmlui/handle/123456789/38995
Title: Heterogeneous speech prediction using LDA classifiers
Authors: Mohd Ridzwan, Tamjis
Muhammad Naufal, Mansor
Ahmad Kadri, Junoh
Amran, Ahmed
Wan Suhana, Wan Daud
Azrini, Idris
mystril_nd@yahoo.com
apairia@yahoo.com
kadri@unimap.edu.my
amranahmed@unimap.edu.my
wsuhana@unimap.edu.my
azrinidris@yahoo.com.my
Keywords: Acoustic measurement
Linear discriminant analysis
Speech intelligibility
Speech quality
Issue Date: Aug-2014
Publisher: Trans Tech Publications
Citation: Advanced Materials Research, vol.1016, 2014, pages 267-272
Abstract: Classroom speech intelligibility has become one of the main concerns in schools and other learning institutions development nowadays. This is because the qualities of student’s perceptions towards teacher are essentials in learning development. Measures have been introduced by the acoustical association to tackle the speech intelligibility problems in the classroom such as room renovations. Room’s acoustics standards have been introduced in several countries but still the questions on whether the standards fits on every classroom in different countries are still arise. Studies have also shown that most of the researches that have been conducted were only focusing on the conventional type classroom which depends only on the teacher’s vocal power. This paper will formulate the measurement protocol on measuring the speech intelligibility in the sound reinforced (multiple speaker) classroom. Finally it was found that the speech intelligibility in the sound reinforced classroom is better than the conventional classroom by using Linear Discriminant Analysis.
Description: Link to publisher's homepage at http://www.ttp.net/
URI: http://dspace.unimap.edu.my:80/xmlui/handle/123456789/38995
ISSN: 1662-8985
Appears in Collections:Intelligent Signal Processing Group (ISP)

Files in This Item:
File Description SizeFormat 
Heterogeneous speech prediction using LDA .pdf174.84 kBAdobe PDFView/Open


Items in UniMAP Library Digital Repository are protected by copyright, with all rights reserved, unless otherwise indicated.