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

Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

6.3K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
6.3K
Force Classification01:22

Force Classification

1.2K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.2K
Perceiving Loudness, Pitch, and Location01:21

Perceiving Loudness, Pitch, and Location

205
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...
205
Extraction: Advanced Methods00:56

Extraction: Advanced Methods

446
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...
446

You might also read

Related Articles

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

Sort by
Same author

Optimizing Voice Sample Quantity and Recording Settings for the Prediction of Type 2 Diabetes Mellitus: Retrospective Study.

JMIR biomedical engineering·2025
Same author

Lysis of Escherichia coli by colicin Ib contributes to bacterial cross-feeding by releasing active β-galactosidase.

The ISME journal·2025
Same author

Longitudinal Changes in Pitch-Related Acoustic Characteristics of the Voice Throughout the Menstrual Cycle: Observational Study.

JMIR formative research·2025
Same author

A Radar-Based Opioid Overdose Detection Device for Public Restrooms: Design, Development, and Evaluation Study.

JMIR biomedical engineering·2024
Same author

Impact of Audio Data Compression on Feature Extraction for Vocal Biomarker Detection: Validation Study.

JMIR biomedical engineering·2024
Same author

A parsimonious model of blood glucose homeostasis.

PLOS digital health·2023
Same journal

Effect of a Spinal Orthosis With Leaf Spring and Programmable Local Vibration on Kyphosis Angle and Trunk Muscle Strength in Hyperkyphosis: Development and Feasibility Study.

JMIR biomedical engineering·2026
Same journal

Psychosocial Stress in the Chinese Community: Speech Analytics Through Linguistic and Acoustic Fusion Using Machine Learning.

JMIR biomedical engineering·2026
Same journal

Remote Monitoring of Bioelectrical Impedance in Patients With Breast Cancer-Related Lymphedema: 1-Year Pilot Longitudinal Study.

JMIR biomedical engineering·2026
Same journal

Age-Related Differences in Joint Kinematics and Spatiotemporal Parameters During Ramp Walking and Level Walking: Cross-Sectional Study.

JMIR biomedical engineering·2026
Same journal

Assessing the Safety and Efficacy of a Noninvasive Device in the Management of Musculoskeletal Pain Using Low-Level Light Therapy: Double-Blinded, Randomized, Placebo-Controlled, Multicentric Study.

JMIR biomedical engineering·2026
Same journal

Increasing Large Language Model Accuracy for Care-Seeking Advice Using Prompts Reflecting Human Reasoning Strategies in the Real World: Validation Study.

JMIR biomedical engineering·2026
See all related articles

Related Experiment Video

Updated: Jun 23, 2025

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

1.5K

Investigation of Deepfake Voice Detection Using Speech Pause Patterns: Algorithm Development and Validation.

Nikhil Valsan Kulangareth1, Jaycee Kaufman1, Jessica Oreskovic1

  • 1Klick Labs, Toronto, ON, Canada.

JMIR Biomedical Engineering
|June 14, 2024
PubMed
Summary
This summary is machine-generated.

This study shows that analyzing speech pauses can effectively distinguish between real human voices and AI-generated deepfake audio. Machine learning models achieved high accuracy in identifying cloned voices based on these biological speech patterns.

Keywords:
artificial intelligenceaudioclonedcloningdeep learningdeepfakedeepfakesmachine learningmodel-naivesoundsoundsspeechtext to speechvocalvocal biomarkersvoice

More Related Videos

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

440
A Protocol for Comprehensive Assessment of Bulbar Dysfunction in Amyotrophic Lateral Sclerosis ALS
12:43

A Protocol for Comprehensive Assessment of Bulbar Dysfunction in Amyotrophic Lateral Sclerosis ALS

Published on: February 21, 2011

34.8K

Related Experiment Videos

Last Updated: Jun 23, 2025

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

1.5K
Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

440
A Protocol for Comprehensive Assessment of Bulbar Dysfunction in Amyotrophic Lateral Sclerosis ALS
12:43

A Protocol for Comprehensive Assessment of Bulbar Dysfunction in Amyotrophic Lateral Sclerosis ALS

Published on: February 21, 2011

34.8K

Area of Science:

  • Digital Forensics
  • Speech Processing
  • Artificial Intelligence

Background:

  • The rise of digital media and deepfake technology poses significant threats to information authenticity.
  • Deepfakes can be misused for impersonation and spreading misinformation, undermining trust in digital content.

Purpose of the Study:

  • To explore the use of innate biological speech characteristics for differentiating authentic human voices from cloned ones.
  • To investigate speech pauses as a key perceptual feature for voice authenticity detection.

Main Methods:

  • Collected voice samples from 49 diverse participants for training voice cloning models.
  • Analyzed speech pauses related to biological and cognitive processes (respiration, swallowing, thinking).
  • Utilized five audio features of speech pause profiles and five machine learning algorithms to build a detection model.

Main Results:

  • Cloned audio showed significant differences in pause duration, speech segment length variation, and pause frequency compared to authentic audio.
  • The AdaBoost machine learning model achieved the highest performance with a balanced accuracy of 0.81 in cross-validation.
  • The optimal model demonstrated a test accuracy of 0.79 on unseen data, validating its generalization capability.

Conclusions:

  • Integrating perceptual, biological speech features into machine learning models shows strong potential for detecting cloned audio.
  • This approach offers a promising method for combating the spread of deepfake audio and verifying voice authenticity.