Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Perceiving Loudness, Pitch, and Location

Perceiving Loudness, Pitch, and Location

The human brain perceives pitch through two primary mechanisms reflected in place theory and frequency theory. Each mechanism describes how sound waves are interpreted as specific pitches by the brain, offering insights into the intricate processes of auditory perception.
Place theory, or place coding, suggests that different pitches are heard because various sound waves activate specific locations along the cochlea's basilar membrane. The brain determines the pitch of a sound by...

Classification of Signals

Classification of Signals

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...

Hearing

Hearing

When we hear a sound, our nervous system is detecting sound waves—pressure waves of mechanical energy traveling through a medium. The frequency of the wave is perceived as pitch, while the amplitude is perceived as loudness.

You might also read

Related Articles

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

Sort by

Same author

Unlocking stable four-electron redox chemistry in aqueous zinc-iodine batteries via solvation structure reconstruction.

Journal of colloid and interface science·2026

Same author

Detrimental influence of high neuroticism on visuospatial selective attention: behavioral and ERP evidence.

Scientific reports·2026

Same author

Genome-Wide and Transcriptomic Analyses Reveal That HcERF37 Activates <i>HcPDR1</i> to Confer Cadmium Tolerance in Kenaf.

Journal of agricultural and food chemistry·2026

Same author

A new approach to discovering a broad-spectrum anti-respiratory virus drug: Tubeimoside II modulates host factor PACT to potentiate the RIG-I antiviral pathway.

Acta pharmaceutica Sinica. B·2026

Same author

Mapping of Neutrophils in Cancers: Insights From Spatial Omics Technologies.

European journal of immunology·2026

Same author

Diagnostic value of short-duration head-up tilt test for unexplained syncope: a non-inferiority study.

BMC cardiovascular disorders·2026

Search research articles

Related Experiment Video

Updated: Oct 22, 2025

Flying Insect Detection and Classification with Inexpensive Sensors

Flying Insect Detection and Classification with Inexpensive Sensors

Published on: October 15, 2014

High Accurate Environmental Sound Classification: Sub-Spectrogram Segmentation versus Temporal-Frequency Attention

Tianhao Qiao¹, Shunqing Zhang¹, Shan Cao¹

¹Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai 200444, China.

Sensors (Basel, Switzerland)

|August 28, 2021

Summary

This summary is machine-generated.

This study introduces a novel framework for environmental sound classification (ESC) using sub-spectrogram segmentation and a convolutional recurrent neural network (CRNN). The proposed methods significantly improve classification accuracy on the ESC-50 dataset.

Keywords:

convolutional recurrent neural network environmental sound classification score level fusion sub-spectrogram segmentation temporal-frequency attention mechanism

More Related Videos

Assessment of Audio-Tactile Sensory Substitution Training in Participants with Profound Deafness Using the Event-Related Potential Technique

Assessment of Audio-Tactile Sensory Substitution Training in Participants with Profound Deafness Using the Event-Related Potential Technique

Published on: September 7, 2022

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

Published on: November 24, 2015

Related Experiment Videos

Last Updated: Oct 22, 2025

Flying Insect Detection and Classification with Inexpensive Sensors

Flying Insect Detection and Classification with Inexpensive Sensors

Published on: October 15, 2014

Assessment of Audio-Tactile Sensory Substitution Training in Participants with Profound Deafness Using the Event-Related Potential Technique

Assessment of Audio-Tactile Sensory Substitution Training in Participants with Profound Deafness Using the Event-Related Potential Technique

Published on: September 7, 2022

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

SSVEP-based Experimental Procedure for Brain-Robot Interaction with Humanoid Robots

Published on: November 24, 2015

Area of Science:

Artificial Intelligence
Machine Learning
Signal Processing

Background:

Effective feature representation is critical for accurate environmental sound classification (ESC).
Traditional methods often struggle to extract optimal representative features from environmental sounds.
Environmental sound classification is a challenging but important field with significant real-world applications.

Purpose of the Study:

To propose a novel ESC classification framework utilizing sub-spectrogram segmentation and score-level fusion.
To enhance classification accuracy by employing a proposed convolutional recurrent neural network (CRNN).
To develop and integrate joint attention mechanisms (temporal, frequency, and global) for improved feature representation.

Main Methods:

A sub-spectrogram segmentation strategy with score-level fusion was developed.
A convolutional recurrent neural network (CRNN) architecture was adopted for classification.
Optimal sub-spectrogram parameters (number and band ranges) were determined through extensive evaluation.
A joint attention mechanism incorporating temporal, frequency, and global attention was proposed.

Main Results:

The proposed ESC classification framework achieved accuracies of 82.1% and 86.4% on the ESC-50 dataset.
These results represent a significant improvement of over 13.5% compared to traditional baseline schemes.
The optimized sub-spectrogram segmentation and attention mechanisms demonstrably enhanced classification performance.

Conclusions:

The proposed sub-spectrogram segmentation with score-level fusion and CRNN framework offers a powerful approach for ESC.
The integration of joint attention mechanisms further boosts the model's ability to capture relevant acoustic features.
This research provides a substantial advancement in the field of environmental sound classification.