Voice Activity Detection Algorithm using Wavelet Band Entropy Ensemble Analysis in Car Noisy Environments

문서 편집 접근성 향상을 위한 음성 명령 기반 모바일 어플리케이션 개발

Abstract

Voice Command systems are important means of ensuring accessibility to digital devices for use in situations where both hands are not free or for people with disabilities. Interests in services using speech recognition technology have been increasing. In this study, we developed a mobile writing application using voice recognition and voice command technology which helps people create and edit documents easily. This application is characterized by the minimization of the touch on the screen and the writing of memo by voice. We have systematically designed a mode to distinguish voice writing and voice command so that the writing and execution system can be used simultaneously in one voice interface. It provides a shortcut function that can control the cursor by voice, which makes document editing as convenient as possible. This allows people to conveniently access writing applications by voice under both physical and environmental constraints.

Fig. 1. Screenshot of (a) Speechnotes (b) Google Docs.

Fig. 2. Transition Diagram of the System.

Fig. 3. System Flow Diagram.

Fig. 4. First page of Application and Command List.

Fig. 5. Screenshot of Application (a)Memo Writing (b) Command List (c) Shortcut Screen.

Fig. 6. Success Rate of Voice Command Group, 95% Confidence Interval.

Fig. 7. Document for Editing (a) Uneditied Document (b) Document with Calibration Marks (c) Final Edited Document * The red mark indicated where the edit should be performed.

Fig. 8. Evaluation Results for Cursor Function, All Charts Include Standard Deviation. (a) Task Completion Time by Applications (b) Success Rate for 28 Sign of Correction by Applications

Table 1. Functions and corresponding commands Provided by the System

Table 2. Configuration of Tasks for Evaluation

Table 3. A table showing whether the task can be per-formed in each application