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 Experiment Videos

Generalized perceptual linear prediction features for animal vocalization analysis.

Patrick J Clemins1, Michael T Johnson

  • 1Speech and Signal Processing Laboratory, Marquette University, P.O. Box 1881, Milwaukee, Wisconsin 53233-1881, USA. patrick.clemins@marquette.edu

The Journal of the Acoustical Society of America
|August 1, 2006
PubMed
Summary

A new generalized perceptual linear prediction (gPLP) model extracts animal vocalization features using species-specific auditory information. This advanced model outperforms traditional methods in analyzing and classifying animal sounds.

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

Music for epilepsy: impact of temporal music structure on intervention outcomes.

Epilepsy & behavior : E&B·2026
Same author

Modeling the sensitivity of cyanobacteria blooms to plausible changes in precipitation and air temperature variability.

The Science of the total environment·2021
Same author

Vaginal spindle cell epithelioma: A first complete MRI and histopathologic description.

Clinical imaging·2018
Same author

Jaw Rotation in Dysarthria Measured With a Single Electromagnetic Articulography Sensor.

American journal of speech-language pathology·2017
Same author

Vocal classification of vocalizations of a pair of Asian small-clawed otters to determine stress.

The Journal of the Acoustical Society of America·2015
Same author

Women seeking second opinion for symptomatic uterine leiomyoma: role of comprehensive fibroid center.

Journal of therapeutic ultrasound·2014

Area of Science:

  • Bioacoustics
  • Signal Processing
  • Animal Communication

Background:

  • Perceptual Linear Prediction (PLP) is widely used for human speech processing.
  • Existing models often fail to capture nuances in animal vocalizations.
  • Species-specific auditory perception data can enhance feature extraction.

Purpose of the Study:

  • To develop a generalized perceptual linear prediction (gPLP) model for animal vocalizations.
  • To integrate species-specific perceptual information into feature extraction.
  • To compare gPLP with traditional PLP models for animal sound analysis.

Main Methods:

  • Adaptation of the PLP model to incorporate frequency warping and equal loudness normalization.
  • Development of a generalized model applicable to various animal species.

Related Experiment Videos

  • Qualitative and quantitative analysis using African elephant and beluga whale vocalizations.

    • Main Results:

    • The gPLP model successfully extracts perceptually relevant features from animal vocalizations.
    • Species-specific models incorporating perceptual information showed improved performance.
    • gPLP demonstrated superior results in visualization and classification tasks compared to standard PLP.

    Conclusions:

    • The gPLP model offers a significant advancement in analyzing animal vocalizations.
    • Integrating species-specific auditory perception enhances the accuracy of bioacoustic analysis.
    • gPLP provides a robust framework for digital signal analysis in bioacoustics.