Automatic speech emotion recognition for arabic dialects: a new dataset and machine learning framework
يناير 01, 2026
DOI: 10.1007/s10586-025-05830-y
Automatic Speech Emotion Recognition (ASER) is a critical aspect of affective computing, which detects emotions in speech to facilitate efficient human-computer interaction. An area that has received little attention in previous research is the Algerian Arabic dialect, which is the setting in which this study examines ASER. We introduce a new corpus, Open Your Heart (OYH), which consists of roughly 6.3 hours of emotional spontaneous speech taken from a talk show on television. A wide variety of emotional expressions are captured in the 6,167 audio clips from 43 male and female speakers that make up the dataset. These expressions are categorized and analyzed through the Geneva Wheel of Emotions (GWE), providing an in-depth understanding of the emotional spectrum. We use the openSMILE toolkit to pull out audio features, then choose the best ones using the Backward Feature Elimination (BFE) method and an improved version that removes the least useful features to make the feature set better. We employ Support Vector Machines (SVM) as the primary classification model, alongside ten additional machine learning classifiers. We assess each model using different numbers of estimators. Among all classifiers, SVM achieves the highest performance, reaching a maximum accuracy of approximately 59% with a complexity of 0.00001. These findings surpass previous benchmarks, demonstrating the robustness of the proposed methodology for emotion recognition in Arabic speech.
Other Researches
An optimized SDN framework for the internet of things
Low-power wireless networks (LPWN) have traditionally been central to the Internet of Things (IoT) discussion. Nevertheless, as these networks grow more complex, their control architectures and protocols reveal significant limitations, particularly ...
Supplier selection strategies evaluation: a multi-agent based simulation
Local food systems have gained prominence in response to increasing consumer demand for locally produced food, driven by heightened interest in diet, food quality, sourcing, production methods, and food safety. These systems support the economic sus...
Inheritance Modeling in Distributed Object-Oriented Design: An Extended G-Nets Model
The emergence of an object-oriented paradigm has been beneficial for complex software development, and this paradigm has been used to develop architectures for distributed systems. Many object-oriented architectures have been suggested for developin...
Retention contracts with asymmetric information: optimistic approach vs pessimistic approach
This paper aims to focus on the utilization of retention contracts to screen and discipline managers in a context in which the council, board of directors, possesses incomplete information about the consequences of managers’ decisions. The analysis ...
Formal Approach to Data Accuracy Evaluation
Usually, data quality is defined by multiple attributes that allow classifying the output data (such as completeness, freshness, and accuracy) or the methods exploiting these data (such as dependability, performance, and protection). Among the sugge...
Retention Contracts under Partial Information Electoral Competition Case Study
This study copes with a class of principal-agent problems where information asymmetry represents an important characteristic. The paper examines the relationship between the principal and agents. The principal has to perform two agents’ screening an...
Prediction Process in Multi-Agent System Online Monitoring: Centralized and Distributed Approaches
This paper discusses the prediction process, which is the main step of the online monitoring process for a multi-agent plan. The monitoring process uses a relational model to estimate the internal status of the system, which is dynamic (changes over...