Feature extraction and classification of malay speech vowels

In human language, a phoneme is the smallest structural unit that distinguishes meaning. Normally, language like English commonly combines phonemes to form a word. In many languages, the Consonant-Vowel (CV) units have the highest frequency of occurrence among different forms of subword units. Th...

Full description

Saved in:

Bibliographic Details
Main Author:	Shahrul Azmi, Mohd Yusof
Format:	Thesis
Language:	English
Subjects:	Consonant-Vowel (CV) Vowel recognition Automatic Speech Recognition (ASR) Linear Discriminat Analysis (LDA) Robustness analysis Malays vowel analysis
Online Access:	http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/12916/1/p.%201-24.pdf http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/12916/2/Full%20Text.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-unimap-12916
record_format	uketd_dc
spelling	my-unimap-129162011-07-01T04:13:24Z Feature extraction and classification of malay speech vowels Shahrul Azmi, Mohd Yusof In human language, a phoneme is the smallest structural unit that distinguishes meaning. Normally, language like English commonly combines phonemes to form a word. In many languages, the Consonant-Vowel (CV) units have the highest frequency of occurrence among different forms of subword units. Therefore, recognition of CV units with a good accuracy is crucial for development of a speech recognition system. There are also many applications that use vowels phonemes. Among them are speech therapy systems that improve utterances of word pronunciation especially to children. There are also systems that teach hearing impaired person to speak properly by pronouncing words with a good degree of intelligibility. All of these systems require high degree of vowel recognition capability in which this study focuses on. This thesis contributes five modified feature extraction methods for vowel recognition based on intensities of the Frequency Filter Bands. They are First Formant Bandwidth (F1BW), Fixed Formant Frequency Band (FFB), Spectral Delta (SpD), Bark Intensity (BrKI) and Formant Frequency Difference (FFD). The performance of these five proposed methods are compared with performance of three conventional feature extraction methods of single frame Mel-frequency cepstrum coefficients (MFCCs), multiple frame Mel-frequency cepstrum coefficients (MFCCf) and the first three formant features. The classifiers analysed in this study were Multinomial Logistic Regression (MLR), Levenberg-Marquardt (LM) network, k-Nearest Neighbors (KNN) and Linear Discriminant Analysis (LDA). There are four main contributions of this thesis. First is the new vowel corpus consisting of more than 1300 recorded vowels from 100 Malaysian speakers. Second are the five improved feature extraction methods which perform better than MFCC on single frame analysis. The third is the performance and robustness analysis using different classifiers and different Gaussian noise level. The fourth contribution is the frame analysis criteria for isolated vowel analysis. Universiti Malaysia Perlis 2010 Thesis en http://dspace.unimap.edu.my/123456789/12916 http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/12916/1/p.%201-24.pdf 30630be59bb3702135e1fb8b4f2a9d46 http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/12916/2/Full%20Text.pdf 171bff503f4f98ec7b830cf4b791088d http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/12916/3/license.txt 394650ff0bafb0a4cb98ff1cbf64f5d2 Consonant-Vowel (CV) Vowel recognition Automatic Speech Recognition (ASR) Linear Discriminat Analysis (LDA) Robustness analysis Malays vowel analysis School of Mechatronic Engineering
institution	Universiti Malaysia Perlis
collection	UniMAP Institutional Repository
language	English
topic	Consonant-Vowel (CV) Vowel recognition Automatic Speech Recognition (ASR) Linear Discriminat Analysis (LDA) Robustness analysis Malays vowel analysis
spellingShingle	Consonant-Vowel (CV) Vowel recognition Automatic Speech Recognition (ASR) Linear Discriminat Analysis (LDA) Robustness analysis Malays vowel analysis Shahrul Azmi, Mohd Yusof Feature extraction and classification of malay speech vowels
description	In human language, a phoneme is the smallest structural unit that distinguishes meaning. Normally, language like English commonly combines phonemes to form a word. In many languages, the Consonant-Vowel (CV) units have the highest frequency of occurrence among different forms of subword units. Therefore, recognition of CV units with a good accuracy is crucial for development of a speech recognition system. There are also many applications that use vowels phonemes. Among them are speech therapy systems that improve utterances of word pronunciation especially to children. There are also systems that teach hearing impaired person to speak properly by pronouncing words with a good degree of intelligibility. All of these systems require high degree of vowel recognition capability in which this study focuses on. This thesis contributes five modified feature extraction methods for vowel recognition based on intensities of the Frequency Filter Bands. They are First Formant Bandwidth (F1BW), Fixed Formant Frequency Band (FFB), Spectral Delta (SpD), Bark Intensity (BrKI) and Formant Frequency Difference (FFD). The performance of these five proposed methods are compared with performance of three conventional feature extraction methods of single frame Mel-frequency cepstrum coefficients (MFCCs), multiple frame Mel-frequency cepstrum coefficients (MFCCf) and the first three formant features. The classifiers analysed in this study were Multinomial Logistic Regression (MLR), Levenberg-Marquardt (LM) network, k-Nearest Neighbors (KNN) and Linear Discriminant Analysis (LDA). There are four main contributions of this thesis. First is the new vowel corpus consisting of more than 1300 recorded vowels from 100 Malaysian speakers. Second are the five improved feature extraction methods which perform better than MFCC on single frame analysis. The third is the performance and robustness analysis using different classifiers and different Gaussian noise level. The fourth contribution is the frame analysis criteria for isolated vowel analysis.
format	Thesis
author	Shahrul Azmi, Mohd Yusof
author_facet	Shahrul Azmi, Mohd Yusof
author_sort	Shahrul Azmi, Mohd Yusof
title	Feature extraction and classification of malay speech vowels
title_short	Feature extraction and classification of malay speech vowels
title_full	Feature extraction and classification of malay speech vowels
title_fullStr	Feature extraction and classification of malay speech vowels
title_full_unstemmed	Feature extraction and classification of malay speech vowels
title_sort	feature extraction and classification of malay speech vowels
granting_institution	Universiti Malaysia Perlis
granting_department	School of Mechatronic Engineering
url	http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/12916/1/p.%201-24.pdf http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/12916/2/Full%20Text.pdf
_version_	1747836765868130304

Feature extraction and classification of malay speech vowels

Similar Items