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

Non-Verbal Cues01:29

Non-Verbal Cues

283
Non-verbal communication extends beyond gestures and facial expressions to include vocal elements known as paralanguage. Paralanguage consists of non-verbal vocal cues such as pitch, loudness, speech rate, pauses, and non-verbal vocalizations like laughter, sighs, and moans. These elements not only accompany speech but also provide critical emotional and contextual information.The Role of Paralanguage in CommunicationParalanguage adds depth to spoken language by conveying emotions and...
283
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

You might also read

Related Articles

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

Sort by
Same author

New design of three-qubit system with three transmons and a single fixed-frequency resonator coupler.

Scientific reports·2025
Same author

Analysis of quantum key distribution based on unified model of sequential state discrimination strategy.

Scientific reports·2024
Same author

Impact of decreased levels of total CO2 on in-hospital mortality in patients with COVID-19.

Scientific reports·2023
Same author

Quantum Contextual Advantage Depending on Nonzero Prior Probabilities in State Discrimination of Mixed Qubit States.

Entropy (Basel, Switzerland)·2021
Same author

Understanding of Various Type of Unambiguous Discrimination in View of Coherence Distribution.

Entropy (Basel, Switzerland)·2020
Same author

Coherence and Entanglement Dynamics in Training Variational Quantum Perceptron.

Entropy (Basel, Switzerland)·2020

Related Experiment Video

Updated: Jan 17, 2026

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.3K

Searching for effective preprocessing method and CNN based architecture with efficient channel attention on speech

Byunggun Kim1, Younghun Kwon2,3

  • 1Department of Applied Artificial Intelligence, Hanyang University(ERICA), Ansan, 425-791, Kyunggi-Do, Republic of Korea.

Scientific Reports
|September 24, 2025
PubMed
Summary
This summary is machine-generated.

This study enhances speech emotion recognition (SER) using convolutional neural networks (CNNs). By optimizing Short-Term Fourier Transform (STFT) preprocessing and incorporating efficient channel attention (ECA), the proposed model achieves superior performance.

Keywords:
Convolutional neural networkData augmentationEfficient channel attentionLog-Mel spectrogramSpeech emotion recognition

More Related Videos

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

2.0K
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

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.3K
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

2.0K
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:

  • Artificial Intelligence
  • Machine Learning
  • Signal Processing

Background:

  • Speech emotion recognition (SER) performance has improved with deep learning.
  • Convolutional Neural Network (CNN) models using spectrograms are popular for SER.
  • Optimal preprocessing and CNN architectures for SER remain unclear.

Purpose of the Study:

  • To investigate effective preprocessing methods and CNN architectures for SER.
  • To enhance emotional feature resolution and channel filter effectiveness in SER models.

Main Methods:

  • Prepared eight datasets with varying frequency-time resolutions for SER.
  • Proposed Short-Term Fourier Transform (STFT) data augmentation with varied window sizes.
  • Designed CNN architectures, including a 6-layer CNN with Efficient Channel Attention (ECA) blocks.

Main Results:

  • Increased frequency resolution in preprocessing improved emotion recognition.
  • CNN models with two ECA blocks outperformed previous SER models.
  • The proposed model with STFT data augmentation achieved the highest SER performance.

Conclusions:

  • Optimized STFT preprocessing and ECA integration are effective for SER.
  • The proposed CNN-based approach offers a significant advancement in speech emotion recognition.
  • Further research can explore advanced attention mechanisms for improved SER.