EMAIL: PASSWORD:
Front Office
UPT. PERPUSTAKAAN
Institut Teknologi Sepuluh Nopember Surabaya


Kampus ITS Sukolilo - Surabaya 60111

Phone : 031-5921733 , 5923623
Fax : 031-5937774
E-mail : libits@its.ac.id
Website : http://library.its.ac.id

Support (Customer Service) :
timit_perpus@its.ac.id




Welcome..guys!

Have a problem with your access?
Please, contact our technical support below:
LIVE SUPPORT


Moh. Fandika Aqsa


Davi Wahyuni


Tondo Indra Nyata


Anis Wulandari


Ansi Aflacha




ITS » Master Theses » Teknik Informatika - S2
Posted by davi at 29/12/2006 14:39:42  •  47079 Views


SISTEM PENGENALAN POLA SUARA DENGAN JARINGAN SYARAF TIRUAN SOM-KOHONEN

VOICE PATTERN OF RECOGNITION SYSTEM WITH THE SOM-KOHONEN OF ARTIFICIAL NEURAL NETWORK

Author :
CANDRA, HERU KARTIKA  




ABSTRAK

Jaringan syaraf tiruan SOM-Kohonen dapat mengenali dan mengklasifikasikan pola-pola suara dengan melakukan pelatihan traininng dari pola-pola vektor input data suara dengan vektor bobot sebagai penghubung antara layar masukkan dan layar kompetisi dalam proses pelatihan. Dari proses pelatihan jaringan syaraf tersebut akan terbentuk cluster-cluster dari pola-pola suara yang dilatihkan. Klasifikasi pola-pola tersebut nantinya dapat digunakan sebagai proses pengenalan pola-pola suara voice recognition yang diujikan. Penentu kevaliditasan proses pelatihan jaringan syaraf tiruan adalah konvergenitas vektor bobot dari tahapan proses pelatihan. Hal tersebut juga ditentukan juga oleh vektor masukkan untuk jaringan. Pada penelitian ini digunakan kartu suara untuk perekaman suara dan perhitungan dengan Linier Prediction Coding yaitu metoda Autokorelasi untuk meminimalisasi akar kuadrat error prediksi dari deretan data suara.


ABSTRACT

The SOM-Kohonen of artificial neural network can classify and identify the voice patterns by training from the voice pattern of voice data input and the weight vector which connects between input layer and competition layer within training process. From that training process of neural network will be formed the clusters from voice patterns that is trained. That classification of patterns can be used as process of voice recognition which is tried. Validity of training process of artificial neural network is determined by converginity of weight vector from training process stage. Such a matter is determined by input vector for network too. In this research it is applied sound card for recording of voice and computation with linier prediction coding that is autocorrelation method to minimize square root of error prediction from voice data row.



KeywordsSom-kohonen; cluster; voice recognition; Linier Prediction Coding
 
Subject:  Perangkat lunak komputer
Contributor
  1. DR. Ir. HANDAYANI TJANDRASA, M.Sc.
Date Create: 29/12/2006
Type: Text
Format: pdf ; 135 pages
Language: Indonesian
Identifier: ITS-Master-3100001012690
Collection ID: 3100001012690
Call Number: 006.3 Can s


Source
Theses Informatics Engineering RT 006.3 Can s, 2000

Coverage
ITS Community

Rights
Copyright @2000 by ITS Library. This publication is protected by copyright and permission should be obtained from the ITS Library prior to any prohibited reproduction, storage in a retrievel system, or transmission in any form or by any means, electronic, mechanical, photocopying, recording, or likewise. For information regarding permission(s), write to ITS Library




[ Download - Summary ]

ITS-Master-3100001012690-388.pdf




 Similar Document...




! ATTENTION !

To facilitate the activation process, please fill out the member application form correctly and completely

Registration activation of our members will process up to max 24 hours (confirm by email). Please wait patiently

POLLING

Bagaimana pendapat Anda tentang layanan repository kami ?

Bagus Sekali
Baik
Biasa
Jelek
Mengecewakan





You are connected from 34.204.0.181
using CCBot/2.0 (https://commoncrawl.org/faq/)



Copyright © ITS Library 2006 - 2019 - All rights reserved.
Dublin Core Metadata Initiative and OpenArchives Compatible
Developed by Hassan