Application of Voiceprint Recognition Technology Based on Channel Confrontation Training in the Field of Information Security

• DOI: 10.3390/electronics12153309
• Publication Date: 2023-08-02T14:57:33Z
• Authors: Suying Gui; Chuan Zhou; Hao Wang; Tiegang Gao
• Keywords: Human voice

With the rapid development of big data, artificial intelligence, and Internet technologies, human–human contact human–machine interaction have led to an explosion voice data. Rapidly identifying speaker’s identity retrieving managing their speech data among massive amount become major challenges for intelligent applications in field information security. This research proposes a vocal recognition technique based on adversarial training speaker audio video as well identification when oriented security domain. The experimental results show that method projects from different scene channels all onto same space dynamically generates interactive representations. It solves channel mismatch problem effectively improves patterns across scenes. is able separate overlapping voices multiple people speak at time reduce separation errors. realizes achieves recall rate 89% large database, which practical value application field.