Article Per Year (5 Year)
p-Index From 2021 - 2026
0
P-Index
This Author published in this journals
All Journal JUSTIN (Jurnal Sistem dan Teknologi Informasi)
Adhitya Teguh Nugraha
Unknown Affiliation
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
PREDIKSI JEDA DALAM UCAPAN KALIMAT BAHASA INDONESIA DENGAN HIDDEN MARKOV MODEL Nugraha, Adhitya Teguh
JUSTIN (Jurnal Sistem dan Teknologi Informasi) Vol 2, No 3 (2014)
Publisher : Jurusan Informatika Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (178.209 KB)

Abstract

This study describes the design of the pauses predictor application of speech sentences in Bahasa Indonesia with Hidden Markov Model (HMM). This application serves to determine the pauses event that occur in Bahasa Indonesia sentences. There are two main processes in this application which is train to train the corpus, and prediction to predict pause. On the train, the input text is produced from sound files, and the output is training corpus for HMM engine. In the prediction process, inputs are words of Bahasa, and outputs are pause prediction that occurred earlier in the input sentence. The results of this study is the sentence that has been predicted in each pause events. Testing is done using precision and recall of training corpus and tagging pause prediction results. The results of precision and recall is calculated back to the f-score. Based on the testing that has been done, showed that the designed applications can already predict a pause in the Indonesian sentences with precision of 0.364, recall of 0.132, and F-score of 0.194 
Co-Authors