Jove
Visualize
Contáctanos
JoVE
x logofacebook logolinkedin logoyoutube logo
ACERCA DE JoVE
Visión GeneralLiderazgoBlogCentro de Ayuda JoVE
AUTORES
Proceso de PublicaciónConsejo EditorialAlcance y PolíticasRevisión por ParesPreguntas FrecuentesEnviar
BIBLIOTECARIOS
TestimoniosSuscripcionesAccesoRecursosConsejo Asesor de BibliotecasPreguntas Frecuentes
INVESTIGACIÓN
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchivo
EDUCACIÓN
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualCentro de Recursos para ProfesoresSitio de Profesores
Términos y Condiciones de Uso
Política de Privacidad
Políticas

Videos de Conceptos Relacionados

Perceiving Loudness, Pitch, and Location01:21

Perceiving Loudness, Pitch, and Location

892
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...
892
Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

8.0K
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...
8.0K
IR Frequency Region: Fingerprint Region01:03

IR Frequency Region: Fingerprint Region

1.8K
IR spectra are divided into two main regions: the diagnostic region and the fingerprint region. The diagnostic region of the spectrum lies above 1500 cm−1. The absorptions resulting from single-bond vibrations of the N–H, C–H, and O–H stretch at higher wavenumbers and appear on the left side of the spectrum. The stretching absorptions of the C≡C and C≡N occur between 2100–2300 cm−1. In contrast, those arising from stretching absorptions of the...
1.8K
Force Classification01:22

Force Classification

2.2K
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,...
2.2K
Extraction: Advanced Methods00:56

Extraction: Advanced Methods

1.0K
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...
1.0K
Detection of Black Holes01:10

Detection of Black Holes

2.5K
Although black holes were theoretically postulated in the 1920s, they remained outside the domain of observational astronomy until the 1970s.
Their closest cousins are neutron stars, which are composed almost entirely of neutrons packed against each other, making them extremely dense. A neutron star has the same mass as the Sun but its diameter is only a few kilometers. Therefore, the escape velocity from their surface is close to the speed of light.
Not until the 1960s, when the first neutron...
2.5K

También podría leer

Artículos Relacionados

Artículos vinculados a este trabajo por autores compartidos, revista y gráfico de citas.

Ordenar por
Same author

Information Entropy-Guided Multi-Scale Feature Fusion for Crowd Density Estimation.

Entropy (Basel, Switzerland)·2026
Same author

Forensics Adapter: Unleashing CLIP for Generalizable Face Forgery Detection.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Integrating Multi-Source and Multi-Temporal UAV Observations to Improve Wheat Yield Prediction Using Machine Learning.

Plants (Basel, Switzerland)·2026
Same author

Low-angular-dependence dynamic structural colors enabled by Sb<sub>2</sub>S<sub>3</sub> phase change material.

Optics letters·2026
Same author

Laser protection thin film compatible with multiband stealth based on metal-dielectric structure.

Optics letters·2026
Same author

CrossDF: improving cross-domain deepfake detection with deep information decomposition.

Frontiers in big data·2025
Same journal

Changes in C-reactive protein levels over time in high-temperature environments using postmortem blood.

Forensic science international·2026
Same journal

Insights from the first synthetic cannabinoid clandestine lab dismantled in Brazil.

Forensic science international·2026
Same journal

Determination of the new psychoactive substances MDMB-4en-PINACA, ADB-BUTINACA and some of their metabolites in blood and urine using DLLE-LC-MS/MS: application to real forensic case samples.

Forensic science international·2026
Same journal

The revolver halo as a forensic marker: Raman spectroscopic evidence of primer-driven gunshot residue deposition.

Forensic science international·2026
Same journal

Research on the effects of signature size on experts' opinions.

Forensic science international·2026
Same journal

Experimental and numerical study of non-penetrating FMJ ballistic impacts on coupled soft and bone tissue surrogates.

Forensic science international·2026
Ver todos los artículos relacionados

Video Experimental Relacionado

Updated: Jan 8, 2026

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

774

Detección forense de audio deepfake mediante características de habla segmentales

Tianle Yang1, Chengzhe Sun2, Siwei Lyu2

  • 1University at Buffalo, Department of Linguistics, Buffalo, 14260, NY, United States.

Forensic science international
|December 12, 2025
PubMed
Resumen
Este resumen es generado por máquina.

Este estudio demuestra que características específicas del sonido del habla pueden detectar eficazmente deepfakes de audio, a diferencia de las características generales del audio. Se propone un nuevo método específico del hablante para una detección forense de deepfakes más precisa.

Palabras clave:
Detección de audio deepfakeHabla deepfakeComparación forense de vocesRelación de verosimilitud

Más Videos Relacionados

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
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K

Videos de Experimentos Relacionados

Last Updated: Jan 8, 2026

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

774
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
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K

Área de la Ciencia:

  • Fonética Acústica
  • Forensia Digital
  • Inteligencia Artificial

Sus antecedentes:

  • El audio Deepfake representa un desafío significativo para la verificación de la autenticidad.
  • Los métodos actuales de detección de deepfakes a menudo se basan en características globales de audio.
  • La replicación de características de habla de articulación fina es difícil para los modelos de generación de deepfakes.

Objetivo del estudio:

  • Investigar la eficacia de las características de sonido del habla segmentales para la detección de audio deepfake.
  • Comparar el rendimiento de las características segmentales frente a las globales en la identificación de deepfakes.
  • Proponer y evaluar un marco novedoso específico del hablante para la detección de deepfakes.

Principales métodos:

  • Análisis de características acústicas de sonidos del habla segmentales.
  • Utilización de características comunes en la comparación forense de voces (FVC).
  • Desarrollo y prueba de un marco de detección de deepfakes específico del hablante.

Principales resultados:

  • Ciertas características segmentales, en particular las utilizadas en FVC, son efectivas para detectar deepfakes de audio.
  • Las características globales de audio mostraron un valor limitado para distinguir deepfakes.
  • El marco propuesto específico del hablante demostró ventajas potenciales sobre los sistemas independientes del hablante.

Conclusiones:

  • Las características acústicas segmentales ofrecen una vía prometedora para la detección de audio deepfake, distinta de los enfoques tradicionales de FVC.
  • Un marco de detección específico del hablante es ventajoso para aplicaciones forenses que requieren alta interpretabilidad y sensibilidad.
  • La investigación futura debería centrarse en refinar los modelos específicos del hablante para una identificación robusta de deepfakes.