Kurdish speaker identification based on one dimensional convolutional neural network

	Kurdish speaker identification based on one dimensional convolutional neural network
Computational Methods for Differential Equations
مقاله 5، دوره 7، Issue 4 (Special Issue)، آبان 2019، صفحه 566-572 اصل مقاله (240.38 K)
نوع مقاله: Research Paper
نویسنده
Zrar Khalid Abdul
Department of applied computer, Charmo University, Sulaymaniyah, Iraq
چکیده
Voice is one of the vital biometrics in human identification and/or verification area. In this paper, two different models are proposed for speaker identification which are a 1D convolutional neural network (CNN) and feature based model. In the feature based model, three global spectral based features including Mel Frequency Cepstral Coefficient (MFCC), Linear Prediction Code (LPC) and Local Binary pattern (LBP) are fed to an SVM and k-NN classifiers. Results show that MFCC is the best feature among the others. Consequently, local MFCC features is extracted from the framed signal and used to both the proposed models. The result shows that the local based MFCC improved the accuracy of the CNN based model.
کلیدواژه‌ها
Convolutional neural network؛ Identification؛ Machine learing

آمار تعداد مشاهده مقاله: 491 تعداد دریافت فایل اصل مقاله: 494

سامانه مدیریت نشریات علمی. قدرت گرفته از سیناوب