Multi-modal person identity authentication is gaining more and more attention in the biometrics area. Combining different modalities increases the performance and robustness of identity authentication systems. The authentication problem is a binary classification problem. The fusion of different modalities can be therefore performed by binary classifiers. We propose to evaluate different binary classification schemes (SVM, MLP, C4.5, Fisher's linear discriminant, Bayesian classifier) on a large database (295 subjects) containing audio and video data. The identity authentication is based on two modalities: face and speech