An Optimization of LPC-16 and HMM-Forward Methods In Virtual Assistant System
Optimalization of Linear Predictive Coding Methods ? 16 and Hidden Markov Forward Models on Virtual Assistant Systems
In general, people today using windows operating system that runs on desktop devices will install many applications as needed. The more applications installed, the more shortcuts that appear in the desktop part of windows. Shortcut itself is an alternative object used to represent so that the user can easily open the application. Users can open without having to open the place where the application is installed. The large number of applications installed on the windows operating system makes shortcuts on the desktop become many and makes it difficult for users to find or open cool applications. Therefore, an application is needed that can assist the user in finding and opening the application easily without making it difficult for the user. The app is a virtual assistant that will assist users in finding and opening the desired application. How it works with the user entering the user's voice and then in the process of extracting the characteristics using the Linear Predictive Coding method and then classified using the Hidden Markov Model Forward method. Once detected, the application will open the application according to the detected sound. This study used 120 training data that were divided into 6 labels consisting of Whatsapp, Linkedin, Tokopedia, Gmail, PowerPoint, and Word. For each label has a training data of 20 data. The data tested amounted to 60. Each label has 10 test data.
Copyright (c) 2021 Chondro seto Nur Suryawan
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Submission of a manuscript implies that the submitted work has not been published before (except as part of a thesis or report, or abstract); that it is not under consideration for publication elsewhere; that its publication has been approved by all co-authors. If and when the manuscript is accepted for publication, the author(s) still hold the copyright and retain publishing rights without restrictions. Authors or others are allowed to multiply the article as long as not for commercial purposes. For the new invention, authors are suggested to manage its patent before published. The license type is CC-BY-SA 4.0.