ISCA Archive IDS 1999
ISCA Archive IDS 1999

About multi-modal identity verification in interactive dialogue systems

Patrick Verlinde, Gérard Chollet, Marc Acheroy

The aim of this paper is to introduce multi­modal identity verification techniques to the Interactive Dialogue Systems society, and to identify possible applications. The multi­modal identity verication system presented here is based on two biometric modalities (speech and vision) and it uses 3 experts (using voice, frontal face and profile images), based on these two modalities, in parallel. Each expert delivers as output a scalar number, called score, stating how well the claimed identity is veried. A fusion module receiving as input the 3 scores has to take a binary decision: accept or reject identity. We have solved this fusion problem using a wide range of statistical pattern recognition techniques. The performances of the different fusion modules have been evaluated and compared on a multi­modal database, containing both vocal and visual modalities.