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

You might also read

Related Articles

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

Sort by
Same author

Bioinformatics screening identifies USP9X as a pathogenic gene underlying thyroid and breast cancer comorbidity.

Journal of molecular histology·2026
Same authorSame journal

Comparative Genomics Reveals Convergent Evolution Between Avivorous Bats (Ia io and Nyctalus aviator).

Integrative zoology·2026
Same author

Nano-selenium spraying during reproductive growth enhances antioxidant capacity, source-sink coordination and grain selenium accumulation in rice.

Plant physiology and biochemistry : PPB·2026
Same author

Microbe-Metabolite Interactions in Cave Soils Synergistically Regulate the Environmental Persistence of Pseudogymnoascus destructans.

Environmental microbiology·2026
Same author

Energy Expenditure Optimization in the Echolocation of <i>Rhinolophus nippon</i>: Evidence from Heart Rate Stability.

Biology·2026
Same author

Acoustic Features and Recognition of Distress Calls in <i>Rhinolophus nippon</i>: A Study Combining Machine Learning and Playback Experiments.

Biology·2026

Related Experiment Video

Updated: Nov 8, 2025

Simultaneous Long-term Recordings at Two Neuronal Processing Stages in Behaving Honeybees
13:55

Simultaneous Long-term Recordings at Two Neuronal Processing Stages in Behaving Honeybees

Published on: July 21, 2014

13.2K

Separating overlapping bat calls with a bi-directional long short-term memory network.

Kangkang Zhang1, Tong Liu1, Shengjing Song1

  • 1Jilin Provincial Key Laboratory of Animal Resource Conservation and Utilization, Northeast Normal University, Changchun, China.

Integrative Zoology
|April 21, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces a deep learning method to separate overlapping bat sounds, improving bioacoustics analysis. The new approach effectively reconstructs animal vocalizations for reliable species classification.

Keywords:
bat vocalizationsbioacousticsdeep neural networksoverlapping callssound separation

More Related Videos

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation
06:09

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Published on: September 8, 2023

743
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

1.8K

Related Experiment Videos

Last Updated: Nov 8, 2025

Simultaneous Long-term Recordings at Two Neuronal Processing Stages in Behaving Honeybees
13:55

Simultaneous Long-term Recordings at Two Neuronal Processing Stages in Behaving Honeybees

Published on: July 21, 2014

13.2K
P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation
06:09

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Published on: September 8, 2023

743
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

1.8K

Area of Science:

  • Bioacoustics
  • Computational Biology
  • Artificial Intelligence

Background:

  • Analyzing animal vocalizations requires clear acoustic signals.
  • Overlapping sounds in bioacoustics hinder the identification of vocal units.
  • Existing solutions for separating overlapping animal sounds are insufficient.

Purpose of the Study:

  • To develop and evaluate a novel method for separating overlapping echolocation-communication calls from multiple bat species.
  • To reconstruct the separated waveforms for further analysis.
  • To demonstrate the practical application of the separated calls in species classification.

Main Methods:

  • A bi-directional long short-term memory network was employed for signal separation.
  • The network was trained to separate overlapping echolocation and communication calls of six bat species.
  • Separation quality was assessed using seven temporal-spectrum parameters and clustering analysis.

Main Results:

  • The deep learning network successfully separated echolocation pulses and communication syllables from overlapping signals.
  • Parameter comparisons showed no significant differences between extracted and original calls.
  • Clustering analysis of separated echolocation calls yielded a high corrected rand index (82.79%), indicating reliable species classification.

Conclusions:

  • The developed deep neural network provides an automated and effective approach for separating overlapping animal sounds.
  • Reconstructed waveforms are suitable for reliable species identification and bioacoustics research.
  • This method advances the application of AI in analyzing complex acoustic environments.