Phonetic-DeepKANet: a robust audio spoofing detection framework for English and Arabic
Muteb Aljasem, Hafsa Ilyas, Ali Javed, Jasim Alnahas, Mohammed Abouheaf · 2026
Read Phonetic-DeepKANet: a robust audio spoofing detection framework for English and Arabic by Muteb Aljasem, Hafsa Ilyas, Ali Javed, Jasim Alnahas, Mohammed Abouheaf (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13346657.txt.
Description
Fake voices can fool speaker checks and drain bank accounts, and Arabic fakes have barely been studied. Muteb Aljasem, Hafsa Ilyas, Ali Javed, Jasim Alnahas, and Mohammed Abouheaf build a detector for two tongues in a 2026 paper. Their net blends deep sound traits with speech-sound features.
A new Arabic fake-voice set fills the data gap. On two English benchmark sets, the method took top scores among dozens of rivals. Its error rate on the Arabic set was 8.06 percent. The blend held up across corpora and attack types. The team offers the set to grow work on neglected languages.
Catalog record
| CREATOR | Muteb Aljasem, Hafsa Ilyas, Ali Javed, Jasim Alnahas, Mohammed Abouheaf |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 86 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |