Educational project on a simple voice identification using mel-frequency cepstrum coefficients and vector quantization

Voice identification is a task of identifying a person based on the content of information in one’s voice signal which distinguishes his/hers from voices of other people. This paper presents an educational project on a simple voice identification system, which uses two parameters of voice features:...

Full description

Bibliographic Details
Main Authors: Akmeliawati, Rini, Widhiputranto, H. K.
Format: Proceeding Paper
Language:English
Published: 2008
Subjects:
Online Access:http://irep.iium.edu.my/14165/
http://irep.iium.edu.my/14165/1/paper794.pdf
_version_ 1848777659502297088
author Akmeliawati, Rini
Widhiputranto, H. K.
author_facet Akmeliawati, Rini
Widhiputranto, H. K.
author_sort Akmeliawati, Rini
building IIUM Repository
collection Online Access
description Voice identification is a task of identifying a person based on the content of information in one’s voice signal which distinguishes his/hers from voices of other people. This paper presents an educational project on a simple voice identification system, which uses two parameters of voice features: the fundamental frequency or pitch and the vocal tract information represented by Mel-Frequency Cepstrum Coefficients (MFCC). The estimation fundamental frequency is performed with Harmonic Product Spectrum (HPS) algorithm, whilst MFCC is calculated using Discrete Cosine Transform, then, is modeled with Vector Quantization to compress the size of data to be processed and to assist identification.
first_indexed 2025-11-14T14:49:30Z
format Proceeding Paper
id iium-14165
institution International Islamic University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T14:49:30Z
publishDate 2008
recordtype eprints
repository_type Digital Repository
spelling iium-141652012-05-23T01:27:08Z http://irep.iium.edu.my/14165/ Educational project on a simple voice identification using mel-frequency cepstrum coefficients and vector quantization Akmeliawati, Rini Widhiputranto, H. K. TK Electrical engineering. Electronics Nuclear engineering Voice identification is a task of identifying a person based on the content of information in one’s voice signal which distinguishes his/hers from voices of other people. This paper presents an educational project on a simple voice identification system, which uses two parameters of voice features: the fundamental frequency or pitch and the vocal tract information represented by Mel-Frequency Cepstrum Coefficients (MFCC). The estimation fundamental frequency is performed with Harmonic Product Spectrum (HPS) algorithm, whilst MFCC is calculated using Discrete Cosine Transform, then, is modeled with Vector Quantization to compress the size of data to be processed and to assist identification. 2008 Proceeding Paper PeerReviewed application/pdf en http://irep.iium.edu.my/14165/1/paper794.pdf Akmeliawati, Rini and Widhiputranto, H. K. (2008) Educational project on a simple voice identification using mel-frequency cepstrum coefficients and vector quantization. In: International Conference on Mechatronics (ICOM'08), 18-20 December 2008, Kuala Lumpur, Malaysia.
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
Akmeliawati, Rini
Widhiputranto, H. K.
Educational project on a simple voice identification using mel-frequency cepstrum coefficients and vector quantization
title Educational project on a simple voice identification using mel-frequency cepstrum coefficients and vector quantization
title_full Educational project on a simple voice identification using mel-frequency cepstrum coefficients and vector quantization
title_fullStr Educational project on a simple voice identification using mel-frequency cepstrum coefficients and vector quantization
title_full_unstemmed Educational project on a simple voice identification using mel-frequency cepstrum coefficients and vector quantization
title_short Educational project on a simple voice identification using mel-frequency cepstrum coefficients and vector quantization
title_sort educational project on a simple voice identification using mel-frequency cepstrum coefficients and vector quantization
topic TK Electrical engineering. Electronics Nuclear engineering
url http://irep.iium.edu.my/14165/
http://irep.iium.edu.my/14165/1/paper794.pdf