iRepository at Perpustakaan UniMAP >
Theses & Dissertations >
School of Mechatronic Engineering (Theses) >

Please use this identifier to cite or link to this item: http://dspace.unimap.edu.my:80/xmlui/handle/123456789/12916

Title: Feature extraction and classification of malay speech vowels
Authors: Shahrul Azmi, Mohd Yusof
Keywords: Consonant-Vowel (CV);Vowel recognition;Automatic Speech Recognition (ASR);Linear Discriminat Analysis (LDA);Robustness analysis;Malays vowel analysis
Issue Date: 2010
Publisher: Universiti Malaysia Perlis
???metadata.dc.publisher.department???: School of Mechatronic Engineering
Abstract: 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.
URI: http://hdl.handle.net/123456789/12916
Appears in Collections:School of Mechatronic Engineering (Theses)

Files in This Item:

File Description SizeFormat
p. 1-24.pdfThis item is protected by original copyright236.73 kBAdobe PDFView/Open
Full Text.pdfAccess is limited to UniMAP community1.33 MBAdobe PDFView/Open
View Statistics

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


Valid XHTML 1.0! Perpustakaan Tuanku syed Faizuddin Putra, Kampus Pauh Putra, Universiti Malaysia Perlis, 02600, Arau Perlis
TEL: +604-9885420 | FAX: +604-9885405 | EMAIL: rujukan@unimap.edu.my Feedback