Speech-based Class Attendance

6th International Conference on Mechatronics

机械制造;无线电电子学

Amri, Umar Faizel^1 ; Nik Hashim, Nik Nur Wahidah^1 ; Mohamad Hanif, Noor Hazrin Hany^1

Department of Mechatronics Engineering, International Islamic University Malaysia, Malaysia^1

关键词: Attendance systems;    Conventional methods;    Department of Engineering;    Identification of individuals;    Mahalanobis distances;    Psychological characteristics;    Recognition rates;    Transition parameter;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/260/1/012008/pdf
DOI  :  10.1088/1757-899X/260/1/012008

来源: IOP

【 摘 要 】

In the department of engineering, students are required to fulfil at least 80 percent of class attendance. Conventional method requires student to sign his/her initial on the attendance sheet. However, this method is prone to cheating by having another student signing for their fellow classmate that is absent. We develop our hypothesis according to a verse in the Holy Qur'an (95:4), "We have created men in the best of mould". Based on the verse, we believe each psychological characteristic of human being is unique and thus, their speech characteristic should be unique. In this paper we present the development of speech biometric-based attendance system. The system requires user's voice to be installed in the system as trained data and it is saved in the system for registration of the user. The following voice of the user will be the test data in order to verify with the trained data stored in the system. The system uses PSD (Power Spectral Density) and Transition Parameter as the method for feature extraction of the voices. Euclidean and Mahalanobis distances are used in order to verified the user's voice. For this research, ten subjects of five females and five males were chosen to be tested for the performance of the system. The system performance in term of recognition rate is found to be 60% correct identification of individuals.