Microcontroller — Controlled security door based on speech recognition

This paper introduced an approach to design and implement a system to control opening of security door by means of the human voice to recognize the password. The aim of this paper is to recognize the speaker and the word to open the door to obtain more security by high recognition rate. This paper proposes Mel-Frequency Cepstral Coefficient (MFCC) technique as feature extraction combined with its first and second derivative including power computation of the speech frames that yields the total multi-dimensional of features, and classification or features matching using Dynamic Time Warping (DTW) which is a good method for computing the similarity between two sequences. The system was trained with three speakers each one have a private password and the test was conducted at twenty two different speakers. The recognition rate performance properly is 100 percent in the real time tests.