Vietnamese Speech Command Recognition using Recurrent Neural Networks
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2019, Vol 10, Issue 7
Abstract
Voice control is an important function in many mobile devices, in a smart home, especially in providing people with disabilities a convenient way to communicate with the device. Despite many studies on this problem in the world, there has not been a formal study for the Vietnamese language. In addition, many studies did not offer a solution that can be expanded easily in the future. During this study, a dataset of Vietnamese speech commands is labeled and organized to be shared with community of general language research and Vietnamese language study in particular. This paper provides a speech collection and processing software. This study also designs and evaluates Recurrent Neural Networks to apply it to the data collected. The average recognition accuracy on the set of 15 commands for controlling smart home devices is 98.19%.
Authors and Affiliations
Phan Duy Hung, Truong Minh Giang, Le Hoang Nam, Phan Minh Duong
Keywords
Related Articles
- EP ID EP611261
- DOI 10.14569/IJACSA.2019.0100728
- Views 131
- Downloads 0
Test Case Generation For Concurrent Object-Oriented Systems Using Combinational Uml Models
Software testing is an important phase of software development to ensure the quality and reliability of the software. Due to some limitations of code based testing method, the researcher has been taken a new method...
A Serious Game for Healthcare Industry: Information Security Awareness Training Program for Hospital Universiti Kebangsaan Malaysia
This paper aims to develop an information security awareness training program for the healthcare industry to ensure the appropriate protection of electronic health systems. Serious games are primarily designed for traini...
Automating the Shaping of Metadata Extracted from a Company Website with Open Source Tools
As part of a market analysis process, the objective was to automate the task of identifying the activities and skills of a collection of enterprises, namely Belgian and French open source companies. In order to avo...
Data fusion based framework for the recognition of Isolated Handwritten Kannada Numerals
combining classifiers appears as a natural step forward when a critical mass of knowledge of single classifier models has been accumulated. Although there are many unanswered questions about matching classifiers to real-...
Enrichment of Object Oriented Petri Net and Object Z Aiming at Business Process Optimization
Software development process is on the basis of two important steps each of which has to be taken seriously, system requirement analysis and system modeling. There have been many different approaches in the literature th...