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 » Undergraduate Theses » Teknologi Informasi - D4
Posted by sarwono@its.ac.id at 23/03/2010 17:46:10  •  3555 Views


CLUSTERING FITUR SUARA VOKAL PADA BAHASA INDONESIA MENGGUNAKAN METODE K-MEANS

CLUSTERING OF INDONESIAN VOWEL VOICE FEATURE USING K-MEANS METHOD

Author :
Joko Prasetyo ( 7405040033 )




ABSTRAK

Pattern recognition merupakan tahapan dalam speech recognition yang fungsinya sebagai tahap pengenalan wicara banyak metode yang telah diterapkan dalam tahap ini seiring berkembangnya teknologi wicara diantaranya Artificial Neural Network Hidden Markov Model Neuro Fuzzy dan lain lain. Pada Proyek Akhir ini akan dibahas mengenai penggunaan metode KMEANS pada pattern recognition dengan tujuan untuk pengelompokan fitur fitur suara vokal Bahasa Indodesia yaitu a i u e o dan . Sebelum tahap pattern recognition terdapat beberapa tahapan yang harus dikerjakan mulai dari proses sampling sampai windowing kemudian pengambilan fitur suara dengan DFT setelah didapatkan fiturs suara yang diinginkan maka dilanjutkan dengan proses pengelompokan dengan K-MEANS dari hasil training terlihat bahwa pengelompokan dengan K-MEANS tidak selalu mendapatkan hasil yang baik tergantung pada terbentuknya centroid di awal sedangkan dari hasil pengujian menunjukkan error kelas a 7.40 i 3.70 u 44.40 e 48.15 o 11.11 dan 7.40.


ABSTRACT

Pattern recognition was the stage in speech recognition that his function as the speech recognition stage many methods that were applied in this stage together with the expansion of speech technology among them Artificial Neural Network Hidden Markov Model Neuro Fuzzy and so on other. In this Final Project will be discussed concerning the use of the method of K-MEANS in pattern recognition with the aim for the grouping features features the Indodesia voice of the Language vowel that is a i u e o and . Before the stage pattern recognition was gotten by several stages that must be done from the process sampling to windowing afterwards the taking fiturs the voice with DFT after being obtained fiturs the voice that was wanted then was followeded by the process of the grouping with K-MEANS from results training was seen that the grouping with K-MEANS always did not get good results of depending on the formation centroid in the beginning whereas from results of the testing showed error the class a 740 i 370 u 4440 e 4815 o 1111 and 740.



KeywordsPattern recognition; Speech recognition; KMEANS; DFT
 
Subject:  Speech recognition
Contributor
  1. Tri Budi Santoso S.T.,M.T.
  2. Nur Rosyid M. S.Kom.
Date Create: 23/03/2010
Type: Text
Format: pdf
Language: Indonesian
Identifier: ITS-Undergraduate-3100010037946
Collection ID: 3100010037946
Call Number: RSEP 006.454 Jok c


Source
Under Graduate, Electrical Industry Engineering, RSEP 006.454 Jok c, 2009

Coverage
ITS Community Only

Rights
Copyright @2009 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 - Open Access ]

  1.  ITS-Undergraduate-8952-7405040033-Abstract_in.pdf - 10 KB
  2.  ITS-Undergraduate-8952-7405040033-Abstract_en.pdf - 10 KB
  3.  ITS-Undergraduate-8952-7405040033-Conclusion.pdf - 10 KB




 Similar Document...

     No similar subject found !


! 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 18.215.33.158
using CCBot/2.0 (https://commoncrawl.org/faq/)



Copyright © ITS Library 2006 - 2020 - All rights reserved.
Dublin Core Metadata Initiative and OpenArchives Compatible
Developed by Hassan