(For USM Staff/Student Only)

EngLib USM > Ω School of Electrical & Electronic Engineering >

Hybrid mfcc and lpc for stuttering assessment using neural network / Choo Chian Choong

Hybrid Mfcc And Lpc For Stuttering Assessment Using Neural Network / Choo Chian Choong
Kegagapan merupakan sejenis gangguan ucapan, di mana ia menghalang seseorang cakap dengan fasih. Penilaian terhadap kegagapan dengan cara tradisional memakan masa dan hasilnya mungkin berbeza bagi pakar penilaian yang berbeza. Sistem penilaian kegagapan akan mengurangkan masa dan hasil penilaian yang lebih consisten. Objektif projek ini adalah untuk membina sistem klasifikasi untuk pemanjangan dan pengulangan dalam ucapan yang gagap dengan menggunakan rangkaian neural. Tiga ciri pengekstrak telah digunakan dalam projek ini, iaitu MFCC, LPC dan hibrid MFCC dan LPC. Aliran projek ini adalah: 1) memperoleh data ucapan gagap; 2) segmentasi perkataan dan kategori; 3) pengekstrak ciri dengan menggunakan 3 cara yang berbeza; 4) Klasifikasi menggunakan corak pengiktirafan neural dalam Matlab. Ketepatan keseluruhan menggunakan 3 beza pengekstrak ciri dalam ANN adalah 84.6% (LPC), 84.6% (MFCC) dan 88.5% (MFCC hibrid dan LPC). Ketepatan klasifikasi terhadap kelas yang beza, pemanjangan, pengulangan dan fasih adalah 66.7%, 92.3% dan 96.3% (hibrid MFCC dan LPC). Sistem klasifikasi pegagapan telah dibina, dengan hibrid MFCC dan LPC sebagai pengekstrak ciri, dan ANN sebagai agen klasifikasi. Keseluruhan ketepatan kalsifikasi adalah 88.5%. _______________________________________________________________________________________ Stuttering is characterized by disfluencies, which disrupt the flow of speech. Traditional way of stuttering assessment is time consuming. The stuttering assessment results always inconsistent between different judges, because human perception on the stuttering event are different for each individual. The stuttering assessment system will reduce the tedious manual work and improve the consistency of the assessment result. The objective of this project is to develop classifier for prolongation and repetition disfluencies in speech using artificial neural network. Three different feature extraction was used in this project, which is Mel Frequency Cepstral Coefficient (MFCC), Linear Prediction Coefficient (LPC) and hybrid MFCC and LPC. The flow of the project were: 1) Stuttered speech data acquisition; 2) Word segmentation and categorization; 3) Feature extraction using 3 different methods; 4) Classification using neural pattern recognition in Matlab. The overall accuracy of the 3 different feature extraction used were 84.6% (LPC), 84.6% (MFCC) and 88.5% (hybrid MFCC and LPC). The classification accuracy using hybrid MFCC and LPC with respect to target classes, which were prolongation, repetition and fluent, were 66.7%, 92.3% and 96.3%. A disfluencies classifier had been developed with hybrid MFCC and LPC as feature extraction and ANN as a classifier. The overall performance of the disfluencies classifier is 88.5%.
Contributor(s):
Choo, Chian Choong - Author
Primary Item Type:
Thesis
Identifiers:
Accession Number : 875005931
Language:
English
Subject Keywords:
Stuttering; disfluencies; hybrid
First presented to the public:
3/1/2016
Original Publication Date:
6/5/2018
Previously Published By:
Universiti Sains Malaysia
Place Of Publication:
School of Electrical & Electronic Engineering
Citation:
Extents:
Number of Pages - 89
License Grantor / Date Granted:
  / ( View License )
Date Deposited
2018-06-05 11:26:58.569
Date Last Updated
2020-06-11 10:01:02.725
Submitter:
Nor Hayati Ismail

All Versions

Thumbnail Name Version Created Date
Hybrid mfcc and lpc for stuttering assessment using neural network / Choo Chian Choong1 2018-06-05 11:26:58.569