ESCA Workshop on Interactive Dialogue in Multi-Modal Systems (IDS-99) June 22-25, 1999 Kloster Irsee, Germany

About Multi-Modal Identity Verification in Interactive Dialogue Systems

Patrick Verlinde (1), Gérard Chollet (2), and Marc Acheroy (1)

(1) Royal Military Academy, Signal and Image Centre, Brussels, Belgium
(2) ENST, Paris, France

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.

Full Paper

Bibliographic reference.  Verlinde, Patrick / Chollet, Gérard / Acheroy, Marc (1999): "About multi-modal identity verification in interactive dialogue systems", In IDS-99, 121-124.