Implementation of the Template Matching Algorithm for Smart Light Control through Speech Recognition for People with Disabilities

Sholihah Ayu Wulandari (Politeknik Negeri Jember, Indonesia)
Adisty Pramudita Putri Rudi (Politeknik Negeri Jember, Indonesia)
Adi Sucipto (Politeknik Negeri Jember, Indonesia)
Bekti Maryuni Susanto (Politeknik Negeri Jember, Indonesia)
Dhony Manggala Putra (Politeknik Negeri Jember, Indonesia)

Jurnal Teknologi Informasi dan Terapan (J-TIT)
Vol 12 No 1 (2025): June

Voice control systems in smart homes provide significant convenience for people with disabilities, especially in operating household devices such as lights without physical interaction. This study develops a voice-based light control system that runs locally on IoT devices using the template matching method. This system utilizes Mel-Frequency Cepstral Coefficients (MFCC) for voice feature extraction and Dynamic Time Warping (DTW) to match test voices with pre-recorded templates. Out of 66 voice samples tested, the system successfully recognized 13 out of 22 voices belonging to the primary user and rejected 43 out of 44 voices from other users, with an accuracy rate of 84.85%. Thus, this system shows potential as an inclusive, efficient, and disability-friendly voice control solution for smart home environments