Automatic Voice-Based Recognition For Automotive Headlights Beam Control

  • W. Astuti Automotive and Robotics Program, Computer Engineering Dept., BINUS ASO School of Engineering, Bina Nusantara University, Jakarta 11480, Indonesia
  • S. Tan Automotive and Robotics Program, Computer Engineering Dept., BINUS ASO School of Engineering, Bina Nusantara University, Jakarta 11480, Indonesia
  • M.I. Solihin Mechatronics Engineering, Faculty of Engineering, UCSI University, Kuala Lumpur 56000, Malaysia
  • R.S. Vincent Automotive and Robotics Program, Computer Engineering Dept., BINUS ASO School of Engineering, Bina Nusantara University, Jakarta 11480, Indonesia
  • B. Michael Automotive and Robotics Program, Computer Engineering Dept., BINUS ASO School of Engineering, Bina Nusantara University, Jakarta 11480, Indonesia
Keywords: Voice-based recognition, Automotive headlight beam control, Artificial Neural Networks, Support vector machines, Mel frequency cepstral coefficient

Abstract

Driving comfort plays an important role in modern automotive technologies. One of the ways of comforting the driver is the voice-based recognition to control car headlights. The driver uttered a ‘specific word’ that is taken as an input to the proposed voice-based recognition system. The proposed mechanism then determines if the signal was either ‘high beam’ or ‘low beam’ to control the car headlights. To activate the headlight’s beam, this voice recognised signal is sent to a processing board. Mel Frequency Cepstral Coefficient (MFCC) is used in the recognition mechanism to extract the uttered word before being fed into Artificial Neural Networks (ANN) and Support Vector Machines (SVM) as a classification engine. The proposed automatic voice-based recognition was evaluated via experimental work. The results show that the proposed automatic voice-based recognition for headlights activation control involving MFCC feature works effectively in which SVM gives slightly better performance accuracy when compared to ANN. In addition to a lesser training time, the resulting accuracy using SVM in the training and testing phase is 93.595% and 91.74% respectively. Meanwhile, ANN has an accuracy of 89.39% and 88.16% in the training and testing respectively.

Published
2021-03-02
How to Cite
Astuti, W., Tan, S., Solihin, M., Vincent, R., & Michael, B. (2021). Automatic Voice-Based Recognition For Automotive Headlights Beam Control. International Journal of Automotive and Mechanical Engineering, 18(1), 8454 -. https://doi.org/10.15282/ijame.18.1.2021.05.0640
Section
Articles