Cover Image

Classroom speech intelligibility prediction using Elman neural network

Link to publisher's homepage at http://ieeexplore.ieee.org/

Saved in:
Bibliographic Details
Main Authors: Paulraj, Murugesa Pandiyan, Prof. Madya, Sazali, Yaacob, Prof. Dr., Ahmad Nazri, Abdullah, M., Thagirarani, M. Ridhwan, Tamjis
Format: Working Paper
Language:English
Published: Institute of Electrical and Electronics Engineers (IEEE) 2010
Subjects:
Neural network
Speech intelligibility
Prediction
Data preprocessing
Online Access:http://dspace.unimap.edu.my/xmlui/handle/123456789/10173
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.unimap-10173
record_format dspace
spelling my.unimap-101732010-11-09T09:07:39Z Classroom speech intelligibility prediction using Elman neural network Paulraj, Murugesa Pandiyan, Prof. Madya Sazali, Yaacob, Prof. Dr. Ahmad Nazri, Abdullah M., Thagirarani M. Ridhwan, Tamjis Neural network Speech intelligibility Prediction Data preprocessing Link to publisher's homepage at http://ieeexplore.ieee.org/ A study was conducted to develop a simple system for classrooms speech intelligibility prediction. In this study, several classrooms properties such as size, signal-to-noise ratio (SNR) and Speech Transmission Index (STI) were collected from different types of classrooms in Universiti Malaysia Perlis (UniMAP). A dataset was obtained from the measurement and was used to develop the system. To develop the system, several process were implemented which includes the statistical analysis, data cleaning and preprocessing, network development, training and classification. In this study, Elman network was selected to develop the system for its robustness in prediction application. The study has also experiments with the network dependency on normalization by comparing different types of normalization method. A simple system for classroom speech intelligibility prediction was developed and it was concluded that network performances are dependent to the normalization method. 2010-11-09T09:07:39Z 2010-11-09T09:07:39Z 2010-05-21 Working Paper p.1-6 978-1-4244-7121-8 http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5545255 http://hdl.handle.net/123456789/10173 en Proceedings of the 6th International Colloquium on Signal Processing & Its Applications (CSPA) 2010 Institute of Electrical and Electronics Engineers (IEEE)
institution Universiti Malaysia Perlis
building UniMAP Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Perlis
content_source UniMAP Library Digital Repository
url_provider http://dspace.unimap.edu.my/
language English
topic Neural network
Speech intelligibility
Prediction
Data preprocessing
spellingShingle Neural network
Speech intelligibility
Prediction
Data preprocessing
Paulraj, Murugesa Pandiyan, Prof. Madya
Sazali, Yaacob, Prof. Dr.
Ahmad Nazri, Abdullah
M., Thagirarani
M. Ridhwan, Tamjis
Classroom speech intelligibility prediction using Elman neural network
description Link to publisher's homepage at http://ieeexplore.ieee.org/
format Working Paper
author Paulraj, Murugesa Pandiyan, Prof. Madya
Sazali, Yaacob, Prof. Dr.
Ahmad Nazri, Abdullah
M., Thagirarani
M. Ridhwan, Tamjis
author_facet Paulraj, Murugesa Pandiyan, Prof. Madya
Sazali, Yaacob, Prof. Dr.
Ahmad Nazri, Abdullah
M., Thagirarani
M. Ridhwan, Tamjis
author_sort Paulraj, Murugesa Pandiyan, Prof. Madya
title Classroom speech intelligibility prediction using Elman neural network
title_short Classroom speech intelligibility prediction using Elman neural network
title_full Classroom speech intelligibility prediction using Elman neural network
title_fullStr Classroom speech intelligibility prediction using Elman neural network
title_full_unstemmed Classroom speech intelligibility prediction using Elman neural network
title_sort classroom speech intelligibility prediction using elman neural network
publisher Institute of Electrical and Electronics Engineers (IEEE)
publishDate 2010
url http://dspace.unimap.edu.my/xmlui/handle/123456789/10173
_version_ 1643789760539394048
score 13.214268

Similar Items