Spoof detection with dynamic learnable sparse attention and tri-modal fusion in resource-constrained audio systems
Xinwei Wang, Zhicheng Tan, Guo Li · 2025
Read Spoof detection with dynamic learnable sparse attention and tri-modal fusion in resource-constrained audio systems by Xinwei Wang, Zhicheng Tan, Guo Li (2025) 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-12755748.txt.
Description
Xinwei Wang, Zhicheng Tan, and Guo Li build in 2025 a lean fake voice spot tool for small sound gear. Voice lock systems face a rise in fake clips from new speech tools. Star spot tools cost too much math and memory for small sensors.
Three sound views feed their frame: two tone maps and the raw wave. A learn sparse focus step picks key traits across the views for the call. A deep back bone reads the raw wave in its own lane. Test error fell to a low mark that beat past tools, at a fifth of the math cost.
Catalog record
| CREATOR | Xinwei Wang, Zhicheng Tan, Guo Li |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 50 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |