Speech Disorder Analysis Using Matching Pursuit and Kohonen Self-Organizing Maps

Abstract

Genetic algorithms (GAs) are stochastic methods that are widely used in search and optimization. The breeding process is the main driving mechanism for GAs that leads the way to find the global optimum. And the initial phase of the breeding process starts with parent selection. The selection utilized in a GA is effective on the convergence speed of the algorithm. A GA can use different selection mechanisms for choosing parents from the population and in many applications the process generally depends on the fitness values of the individuals. Artificial neural networks (ANNs) are used to decide the appropriate parents by the new hybrid algorithm proposed in this study. And the use of neural networks aims to produce better offspring during the GA search. The neural network utilized in this algorithm tries to learn the structural patterns and correlations that enable two parents to produce high-fit offspring. In the breeding process, the first parent is selected based on the fitness value as usual. Then it is the neural network that decides the appropriate mate for the first parent chosen. Hence, the selection mechanism is not solely dependent on the fitness values in this study. The algorithm is tested with seven benchmark functions. It is observed from results of these tests that the new selection method leads genetic algorithm to converge faster.

External vs. Internal SVM-Rfe: The SVM-Rfe Method Revisited and Applied to Emotion Recognition

“…One important challenge of the speech emotion recognition is the extraction of relevant features that are efficiently informative on the existing emotions. In the literature, different types of speech features are used [2,12,29], we focus on basic acoustic features since (i) we assume that the acoustic information is fully given by a set of both prosodic and spectral features and (ii) the use of these acoustic features is still an active research domain in emotion recognition [30]. We propose to study four separation problems: "Happy" versus "Neutral", "Cold anger" versus "Neutral", "Hot anger" versus "Neutral" and "Panic" versus "Neutral".…”