A method and system for counterfeit audio authentication

Abstract

The present application relates to the technical field of audio discrimination, and discloses a counterfeit audio discrimination method and system, the method comprising: performing frame windowing processing on original audio data to obtain frame sequence audio data; performing short-time Fourier transform on the frame sequence audio data to obtain frequency domain representation data and an initial acoustic feature vector; performing deep feature reconstruction on the initial acoustic feature vector, and performing multi-modal feature fusion on the reconstructed feature tensor and the frame sequence audio data to obtain a joint discrimination feature set; performing timing context analysis on the joint discrimination feature set to capture feature dependency relationships of the frame sequence audio data, and obtaining a context-enhanced feature sequence; quantifying the cosine similarity between the context-enhanced feature sequence and a real voiceprint template, and analyzing the feature mutation amplitude of the context-enhanced feature sequence to obtain a double discrimination metric; and performing comprehensive scoring on the double discrimination metric to obtain an audio discrimination conclusion; the present application can improve the efficiency of counterfeit audio discrimination.

Images