Novel transfer learning based acoustic feature engineering for scene fake audio detection
Abstract Audio forensics plays a major role in the investigation and analysis of audio recordings for legal and security purposes. The advent of audio fake attacks using speech combined with scene-manipulated audio represents a sophisticated challenge in fake audio detection. Fake audio detection, a...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-03-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-93032-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850030057739780096 |
|---|---|
| author | Ahmad Sami Al-Shamayleh Hafsa Riasat Ala Saleh Alluhaidan Ali Raza Sahar A. El-Rahman Diaa Salama AbdElminaam |
| author_facet | Ahmad Sami Al-Shamayleh Hafsa Riasat Ala Saleh Alluhaidan Ali Raza Sahar A. El-Rahman Diaa Salama AbdElminaam |
| author_sort | Ahmad Sami Al-Shamayleh |
| collection | DOAJ |
| description | Abstract Audio forensics plays a major role in the investigation and analysis of audio recordings for legal and security purposes. The advent of audio fake attacks using speech combined with scene-manipulated audio represents a sophisticated challenge in fake audio detection. Fake audio detection, a critical technology in modern digital security, addresses the growing threat of manipulated audio content across various applications, including media, legal evidence, and cybersecurity. This research proposes a novel transfer learning approach for fake audio detection. We utilized a benchmark dataset, SceneFake, that contains 12,668 audio signal files for both real and fake scenes. We propose a novel transfer learning method, which initially extracts mel-frequency cepstral coefficients (MFCC) and then class prediction probability value features. The newly generated transfer features set by the proposed MfC-RF (MFCC-Random Forest) are utilized for further experiments. Results expressed that using the MfC-RF features random forest method outperformed existing state-of-the-art methods with a high-performance measure accuracy of 0.98. We have tuned hyperparameters of applied machine learning approaches, and cross-validation is applied to validate performance results. In addition, the complexity of the computation is measured. The proposed research aims to enhance the accuracy measure, and efficiency of identifying manipulated audio content, thereby contributing to the integrity and reliability of digital communications. |
| format | Article |
| id | doaj-art-cd1d080ae7d94432add0b1ce3e6d028d |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-cd1d080ae7d94432add0b1ce3e6d028d2025-08-20T02:59:19ZengNature PortfolioScientific Reports2045-23222025-03-0115111310.1038/s41598-025-93032-2Novel transfer learning based acoustic feature engineering for scene fake audio detectionAhmad Sami Al-Shamayleh0Hafsa Riasat1Ala Saleh Alluhaidan2Ali Raza3Sahar A. El-Rahman4Diaa Salama AbdElminaam5Department of Data Science and Artificial Intelligence, Faculty of Information Technology, Al-Ahliyya Amman UniversityDepartment of Computer Science/SST, University of Management and TechnologyDepartment of Information Systems, College of Computer and Information Science, Princess Nourah Bint Abdulrahman UniversityDepartment of Software Engineering, University Of LahoreComputer Systems Program-Electrical Engineering Department, Faculty of Engineering-Shoubra, Benha UniversityFaculty of Computers, Misr International UniversityAbstract Audio forensics plays a major role in the investigation and analysis of audio recordings for legal and security purposes. The advent of audio fake attacks using speech combined with scene-manipulated audio represents a sophisticated challenge in fake audio detection. Fake audio detection, a critical technology in modern digital security, addresses the growing threat of manipulated audio content across various applications, including media, legal evidence, and cybersecurity. This research proposes a novel transfer learning approach for fake audio detection. We utilized a benchmark dataset, SceneFake, that contains 12,668 audio signal files for both real and fake scenes. We propose a novel transfer learning method, which initially extracts mel-frequency cepstral coefficients (MFCC) and then class prediction probability value features. The newly generated transfer features set by the proposed MfC-RF (MFCC-Random Forest) are utilized for further experiments. Results expressed that using the MfC-RF features random forest method outperformed existing state-of-the-art methods with a high-performance measure accuracy of 0.98. We have tuned hyperparameters of applied machine learning approaches, and cross-validation is applied to validate performance results. In addition, the complexity of the computation is measured. The proposed research aims to enhance the accuracy measure, and efficiency of identifying manipulated audio content, thereby contributing to the integrity and reliability of digital communications.https://doi.org/10.1038/s41598-025-93032-2 |
| spellingShingle | Ahmad Sami Al-Shamayleh Hafsa Riasat Ala Saleh Alluhaidan Ali Raza Sahar A. El-Rahman Diaa Salama AbdElminaam Novel transfer learning based acoustic feature engineering for scene fake audio detection Scientific Reports |
| title | Novel transfer learning based acoustic feature engineering for scene fake audio detection |
| title_full | Novel transfer learning based acoustic feature engineering for scene fake audio detection |
| title_fullStr | Novel transfer learning based acoustic feature engineering for scene fake audio detection |
| title_full_unstemmed | Novel transfer learning based acoustic feature engineering for scene fake audio detection |
| title_short | Novel transfer learning based acoustic feature engineering for scene fake audio detection |
| title_sort | novel transfer learning based acoustic feature engineering for scene fake audio detection |
| url | https://doi.org/10.1038/s41598-025-93032-2 |
| work_keys_str_mv | AT ahmadsamialshamayleh noveltransferlearningbasedacousticfeatureengineeringforscenefakeaudiodetection AT hafsariasat noveltransferlearningbasedacousticfeatureengineeringforscenefakeaudiodetection AT alasalehalluhaidan noveltransferlearningbasedacousticfeatureengineeringforscenefakeaudiodetection AT aliraza noveltransferlearningbasedacousticfeatureengineeringforscenefakeaudiodetection AT saharaelrahman noveltransferlearningbasedacousticfeatureengineeringforscenefakeaudiodetection AT diaasalamaabdelminaam noveltransferlearningbasedacousticfeatureengineeringforscenefakeaudiodetection |