Towards the Development of a Real-Time Deepfake Audio Detection System in Communication Platforms
It addresses the need for real-time audio stream security in communication platforms, but is incremental as it adapts existing models to a real-time context.
This study tackled the problem of deepfake audio threats in communication platforms by developing a real-time detection system using Resnet and LCNN models on the ASVspoof 2019 dataset, achieving benchmark performances comparable to existing baselines.
Deepfake audio poses a rising threat in communication platforms, necessitating real-time detection for audio stream integrity. Unlike traditional non-real-time approaches, this study assesses the viability of employing static deepfake audio detection models in real-time communication platforms. An executable software is developed for cross-platform compatibility, enabling real-time execution. Two deepfake audio detection models based on Resnet and LCNN architectures are implemented using the ASVspoof 2019 dataset, achieving benchmark performances compared to ASVspoof 2019 challenge baselines. The study proposes strategies and frameworks for enhancing these models, paving the way for real-time deepfake audio detection in communication platforms. This work contributes to the advancement of audio stream security, ensuring robust detection capabilities in dynamic, real-time communication scenarios.