Application of ABM to Spectral Features for Emotion Recognition
Journal Title: Mehran University Research Journal of Engineering and Technology - Year 2018, Vol 37, Issue 4
Abstract
ER (Emotion Recognition) from speech signals has been among the attractive subjects lately. As known feature extraction and feature selection are most important process steps in ER from speech signals. The aim of present study is to select the most relevant spectral feature subset. The proposed method is based on feature selection with optimization algorithm among the features obtained from speech signals. Firstly, MFCC (Mel-Frequency Cepstrum Coefficients) were extracted from the EmoDB. Several statistical values as maximum, minimum, mean, standard deviation, skewness, kurtosis and median were obtained from MFCC. The next process of study was feature selection which was performed in two stages: In the first stage ABM (Agent-Based Modelling) that is hardly applied to this area was applied to actual features. In the second stageOpt-aiNET optimization algorithm was applied in order to choose the agent group giving the best classification success. The last process of the study is classification. ANN (Artificial Neural Network) and 10 cross-validations were used for classification and evaluation. A narrow comprehension with three emotions was performed in the application. As a result, it was seen that the classification accuracy was rising after applying proposed method. The method was shown promising performance with spectral features.
Authors and Affiliations
Semiye Demircan, Humar Kahramanli
Keywords
Related Articles
- EP ID EP391831
- DOI 10.22581/muet1982.1804.01
- Views 116
- Downloads 0
On (Non) Applicability of a Mode-Truncation of a Damped Traveling String
This study investigates a linear homogeneous initial-boundary value problem for a traveling string under linear viscous damping. The string is assumed to be traveling with constant speed, while it is fixed at both ends....
Energy and Exergy Analysis of a Coal Fired Power Plant
In this paper, energy and exergy analysis has been conducted on a subcritical coal fired power plant of Wisconsin Power and Light Company, USA to investigate the steam cycle energy and exergy efficiency. The cycle is ana...
Antecedents of Enterprise Resource Planning and its Impact on Firm Perfromance with Supply Chain Integration as Mediating factor
In today's knowledge based globalized business world, the contemporary organizations are thriving to apply the innovative as well as modern business techniques and tools in their products and processes regularly. Besides...
A Novel Zero-Watermarking Based Scheme for Copyright Protection of Grayscale Images
Zero-watermarking of digital images is a powerful method with respect to transparency in the watermarked image. However, robustness is still a challenging characteristic for researchers. The proposed method of zero-water...
Augmentation of Fatigue and Tensile Strength of AA-6061 Processed through Equal Channel Angular Pressing
ECAP (Equal Channel Angular Pressing) is a technique used to enhance the strength of material by grain refinement. In this research, an aerospace grade aluminum alloy-6061 is investigated. The specimens were pressed thro...