What question did this study set out to answer?

The study aims to improve deepfake audio detection using transfer learning and data augmentation techniques.

June 17, 2026Computers, materials & continua/Computers, materials & continua (Print)Open Access

Fine-Tune Transfer Learning Model for Deepfake Audio Detection Using Hybrid Features and Data Augmentation

View Full Paper

Ask AI

Bookmark

The study aims to improve deepfake audio detection using transfer learning and data augmentation techniques.
Developed a framework using fine-tuned pre-trained models: ResNet50, VGGish, and YAMNet.
Implemented systematic data augmentation to enhance training sample diversity.
Conducted feature fusion and selection before using a lightweight model for classification.
Achieved an accuracy of 99.7% in detecting deepfake audio.
Outperformed individual baseline models in performance and generalization across different acoustic conditions.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Randomized trial demonstrates effective detection of deepfake audio in diverse conditions, indicating its importance for digital communication safety.

Cite This Study

Jahangir et al. (2026) studied this question.

synapsesocial.com/papers/6a323e36d50b63ecad20796e https://doi.org/10.32604/cmc.2026.080593

View Full Paper

Ask AI

Bookmark

Implication

Randomized trial demonstrates effective detection of deepfake audio in diverse conditions, indicating its importance for digital communication safety.

Fine-Tune Transfer Learning Model for Deepfake Audio Detection Using Hybrid Features and Data Augmentation

Key Points

Discussion

Implication

Cite This Study

Fine-Tune Transfer Learning Model for Deepfake Audio Detection Using Hybrid Features and Data Augmentation

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider