Please use this identifier to cite or link to this item:
http://dspace.unimap.edu.my:80/xmlui/handle/123456789/6869
Title: | Vowel recognition based on frequency ranges determined by bandwidth approach |
Authors: | Paulraj, M. P. Sazali, Yaacob Mohd Yusof, S. A. |
Keywords: | Feature extraction Speech recognition Natural language processing Multilayer perceptrons Digital electronics Signal theory (Telecommunication) Automatic speech recognition Speech perception |
Issue Date: | Jul-2009 |
Publisher: | Institute of Eelectrical and Electronics Engineering (IEEE) |
Citation: | p.75-79 |
Series/Report no.: | Proceedings of the International Conference on Audio, Language and Image Processing (ICALIP 08) |
Abstract: | Automatic speech recognition (ASR) has made great strides with the development of digital signal processing hardware and software especially using English as the language of choice. In this paper, a new feature extraction method is presented to identify vowels recorded from 80 Malaysian speakers. The features were obtained from Vocal Tract Model based on Bandwidth (BW) approach. Bandwidth approach identifies frequency bands based on the first peak of vowel frequency responses. Mean and maximum energies were calculated from these Bandwidth frequency bands. Classification results from Bandwidth Approach were compared with the first 3-formant features using Linear Predictive method. A Multi-Layer Perceptron (MLP) and Multinomial Logistic Regression (MLR) were used to classify the vowels. MLR and MLP shows comparable classification results for BW approach of 96.40% and 96.59% respectively. Bandwidth approach obtained 5.49% higher classification rate than 3-formant features using MLP. |
Description: | Link to publisher's homepage at http://ieeexplore.ieee.org |
URI: | http://ieeexplore.ieee.org/xpls/abs_all.jsp?=&arnumber=4590133 http://dspace.unimap.edu.my/123456789/6869 |
ISBN: | 978-1-4244-1723-0 |
Appears in Collections: | School of Mechatronic Engineering (Articles) Sazali Yaacob, Prof. Dr. Paulraj Murugesa Pandiyan, Assoc. Prof. Dr. |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Abstract.pdf | 7.7 kB | Adobe PDF | View/Open |
Items in UniMAP Library Digital Repository are protected by copyright, with all rights reserved, unless otherwise indicated.