Pembelajaran membaca huruf alfabet dengan teknologi pengolahan suara

Chamidy, Totok and Kusumawati, Ririen (2016) Pembelajaran membaca huruf alfabet dengan teknologi pengolahan suara. Research Report. Lembaga Penelitian dan Pengabdian kepada Masyarakat UIN Maulana Malik Ibrahim, Malang. (Unpublished)

[img]
Preview
Text
totokchamidy-rpiinter-2016.pdf

Download (17MB) | Preview

Abstract

Structural Analytical and Synthetic (SAS) is one method used to read the beginning of the learning process for beginners. Learning to read about the SAS method begins by displaying and introducing a complete sentence. The sentence decomposed into smaller units called word. Analyzing or decomposition process continues until the manifestation of the smallest unit of speech that cannot be described again, namely letters. Computer-based Technology can be a means to learn to read. Learning to read can be built using a computer, now it can be said is a fun learning media. Early reading of learning based on this computer is adopting the SAS method in combination with voice recognition technology. Learners say the letter and examined whether or not by a computer using voice recognition technology.

In this study, the system displays the word or alphabet of the sentence pronounced by learners. Furthermore, the learner tries to pronounce the sentence in front of a microphone that has been provided. The results of voice input spoken by learners examined whether or not using voice processing technology. This research applies speech recognition systems by using the Speech Application Program Interface (SAPI) version 5.4 Microsoft Speech Engine, which was developed by Microsoft Corporation.

The conclusion of this study is the noise level affects whether or not to recognize the sound being examined, the difficulty in recognizing the voice being examined the higher of noise level. Alphabet that can be recognized properly by the Indonesian pronunciation has on accuracy above 50% for the test without training and using training is the 'S' and 'N' alphabet.

Item Type: Research (Research Report)
Subjects: 08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080107 Natural Language Processing
Divisions: Faculty of Technology > Department of Informatics Engineering
Depositing User: Miftahus Sholehudin
Date Deposited: 10 Jan 2017 14:22

Downloads

Downloads per month over past year

Origin of downloads

Actions (login required)

View Item View Item