Dhwani Deepfake Audio Detection System
Dhwani is an AI-based system for detecting audio deepfakes. Analyzes both how speech sounds and how it changes over time. Uses a hybrid model combining CNN and Bi-LSTM. Helps identify fake audios
視頻
技術堆疊
描述
With therise of AI-generated synthetic voices (audio deepfakes), it’s becoming increasingly difficult to verifythe authenticity of audio clips. Thesefakes can be misused in misinformation, fraud, and impersonation attacks.Dhwani means “sound” in Sanskrit. It is an AI-based system for detecting audio deepfakes. Analyzes both how speech sounds and how it changes over time. Uses a hybrid model combining CNN and Bi-LSTM. Helps identify fake or AI-generated voices with high reliability.To create and deploy a system that can effectively separate real from AI-synthesized audio. Using ml dl system should able to study audio features and identify irregularities reflecting deepfake. Aims to increase the dependability of digital audio communications as well as the fight against misinformation spreading.