Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Labeling Emotion01:20

Labeling Emotion

601
Emotional labeling is a cognitive process that involves identifying and naming one's emotions, such as anger, fear, happiness, or sadness. It allows individuals to recognize and express their internal emotional states, a critical aspect of emotional regulation and communication. Labeling emotions requires more than mere recognition; it also involves drawing upon memory and contextual cues to understand the current situation and apply a corresponding emotional label. For instance, feeling...
601
Classification of Signals01:30

Classification of Signals

1.3K
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
1.3K
Coping Strategies: Emotion Focused01:20

Coping Strategies: Emotion Focused

435
Emotion-focused coping refers to a set of strategies aimed at managing the emotional impact of stressors, rather than directly addressing their causes. This approach involves altering one's emotional response to stressful situations to reduce their psychological effects. For example, individuals might talk with a friend or engage in activities like journaling to express their feelings. Such actions can help achieve emotional clarity or release, providing the psychological stability needed...
435
Extraction: Advanced Methods00:56

Extraction: Advanced Methods

1.1K
Metal ions can be separated from one another by complexation with organic ligands–the chelating agent– to form uncharged chelates. Here, the chelating agent must contain hydrophobic groups and behave as a weak acid, losing a proton to bind with the metal. Since most organic ligands used in this process are insoluble or undergo oxidation in the aqueous phase, the chelating agent is initially added to the organic phase and extracted into the aqueous phase. The metal-ligand complex is...
1.1K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Distilroberta2gnn: a new hybrid deep learning approach for aspect-based sentiment analysis.

PeerJ. Computer science·2024
Same author

Human-Computer Interaction with Detection of Speaker Emotions Using Convolution Neural Networks.

Computational intelligence and neuroscience·2022
Same author

Human-Computer Interaction for Recognizing Speech Emotions Using Multilayer Perceptron Classifier.

Journal of healthcare engineering·2022
Same author

Two-Way Feature Extraction for Speech Emotion Recognition Using Deep Learning.

Sensors (Basel, Switzerland)·2022

Related Experiment Video

Updated: Jan 17, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.9K

Feature selection for emotion recognition in speech: a comparative study of filter and wrapper methods.

Alaa Altheneyan1, Aseel Alhadlaq1

  • 1Department of Computer Science and Engineering, College of Applied Studies, King Saud University, Riyadh, Saudi Arabia.

Peerj. Computer Science
|September 24, 2025
PubMed
Summary

Feature selection methods like mutual information (MI) significantly improve speech emotion recognition models. MI achieved the highest performance by selecting optimal features, enhancing accuracy and reducing model complexity.

Keywords:
Artificial intelligenceFeature extractionMachine learningPattern recognitionSpeech emotion recognition

More Related Videos

Asthma Detection Research Based on Voice Signal Processing and Machine Learning
04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

930
Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury
05:51

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury

Published on: May 15, 2016

9.4K

Related Experiment Videos

Last Updated: Jan 17, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.9K
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

930
Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury
05:51

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury

Published on: May 15, 2016

9.4K

Area of Science:

  • Speech Emotion Recognition
  • Machine Learning
  • Signal Processing

Background:

  • Feature selection is crucial for optimizing speech emotion recognition (SER) models.
  • Complexity and irrelevant data can hinder SER model performance.
  • Evaluating feature selection methods is key to advancing SER.

Purpose of the Study:

  • To evaluate correlation-based (CB), mutual information (MI), and recursive feature elimination (RFE) for SER.
  • To compare these methods against baseline approaches using diverse feature sets.
  • To determine the impact of feature selection on SER model performance metrics.

Main Methods:

  • Utilized three feature sets: all 170 features, a 163-feature subset, and a 157-feature subset.
  • Applied CB, MI, and RFE feature selection techniques.
  • Compared methods based on accuracy, precision, recall, and F1-score.

Main Results:

  • Using all features yielded 61.42% accuracy, often with irrelevant data.
  • MI with 120 features achieved the highest performance (65% precision, recall, F1-score, 64.71% accuracy).
  • CB methods offered a good balance of simplicity and accuracy; RFE improved with more features.

Conclusions:

  • Mutual Information (MI) is a highly effective feature selection method for SER.
  • Optimizing feature sets through selection enhances SER model performance.
  • Feature selection balances model complexity and recognition accuracy.