انجمن کامپیوتر ایران

In a quest for modeling human brain, we are going to introduce a brain model based on a general framework for brain called Memory-Prediction Framework. The model is a hierarchical Bayesian structure that uses Reservoir Computing methods as the state-of-the-art and the most biological plausible Temporal Sequence Processing method for online and unsupervised learning. So, the model is called Hierarchical Bayesian Reservoir Memory (HBRM). HBRM uses a simple stochastic gradient descent learning algorithm to learn and organize common multi-scale spatio-temporal patterns/features of the input signals in a hierarchical structure in an unsupervised manner to provide robust and real-time prediction of future inputs. We suggest HBRM as a real-time high-dimensional stream processing model for the basic brain computations. In this paper we will describe the model and assess its prediction accuracy in a simulated real-world environment.

Gender identification based on speech signal has become gradually a matter of concern in recent years. In this context 6 feature types including MFCC, LPC, RC, LAR, pitch values and formants are compared for automatic gender identification and three best feature types are selected using four feature selection techniques. These techniques are GMM, Decision Tree, Fisher’s Discriminant Ratio, and Volume of Overlap Region. A dimension reduction is done on the best three feature types and the best coefficients are then selected from each feature vector. Selected coefficients are evaluated for gender classification using three types of classifiers including GMM, SVM and MLP neural network. 96.09% gender identification performance was obtained as the best performance using the selected coefficients and MLP classifier.