An Attention-Based Command Detection Model to Allow Natural Language in Voice Control System

Abstract

Interaction with machines using speech has been a popular research topic in recent years. Considerable amount of work focuses on the improvement of voice control systems which utilize automatic speech recognition (ASR) and natural language processing (NLP) technologies to recognize user’s speech and extract executable commands. The existing voice control systems usually do not take into count the diversity and richness of natural language and require users to follow pre-defined keywords or grammar rules. To address this limitation, we designed and implemented a voice control system that supports natural language, utilizing an attention-based command detection model. Our system supports flexible voice instructions and the user does not need to follow any pre-defined rules. An Arduino 4WD robot car was also built in this paper to verify the system. In the experiments, the accuracy of command detection on natural language reaches 0.993 in our developed dataset. Besides, the realization of the 3-DOF (degree of freedom) motion control on our robot car suggests the feasibility of using our proposed system to control any functionality or behavior of the hardware system. Our work improves the flexibility and usability of voice control systems by applying technologies in the domain of NLP.