Web-Based Automation Speech-to-Text Application using Audio Recording for Meeting Speech

作     者：Muhammad Yasir Marlince NK Nababan Yonata Laia Windania Purba Robin Asaziduhu Gea 

作者机构：Faculty of Technology and Computer Science Universitas Prima Indonesia Indonesia STMIK Mikroskil Medan Indonesia Department of Information System Faculty of Technology and Computer Sciences Universitas Methodist Indonesia Indonesia 

出 版 物：《Journal of Physics: Conference Series》 

年 卷 期：2019年第1230卷第1期

学科分类：07[理学] 0702[理学-物理学] 

摘      要：The use of technology is very important nowadays. Most of everyday activities are documented and stored in digital form. One of those activity is recording. Activity of an organization is very important, therefore recording of meeting material is one of those important activities. Usually the meeting material is documented by writing them into papers or typing them and stored them into computer. Sometimes, the meeting information is written or typed incorrectly so a speech-to-text application is required to solve this problem. In this study, the solution offered is to implement a web-based automation speed-to-text application which can record the voice of meeting participants then converted them into text automatically, so the results of the recording process of meeting materials are more effective and efficient By using voice recognition feature its called web kit Speech Recognition, this system can be implemented. After successfully implementing this application which is so called Speech Meeting Web kit system, the average value for duration system for Indonesia and English language is 96,63 % and 82,78 %.