Combined handwriting and speech modalities for user authentication
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans - Special section: Best papers from the 2007 biometrics: Theory, applications, and systems (BTAS 07) conference
Modelling combined handwriting and speech modalities
ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics
Hi-index | 0.00 |
We are proposing a novel and efficient user authenti- cation system using combined acquisition of online hand- writing and speech signals. In our approach, signals are recorded by asking the user to say what she or he is simulta- neously writing. This methodology has the clear advantage of acquiring two sources of biometric information at no ex- tra cost in terms of time or inconvenience. We have built a straightforward verification system to model these sig- nals using statistical models. It is composed of two Gaus- sian Mixture Models (GMMs) sub-systems that takes as in- put features extracted from the pen and voice signals. The system is evaluated on MyIdea, a realistic multimodal bio- metric database. Results show that the use of both speech and handwriting modalities outperforms significantly these modalities used alone. We also report on the evaluations of different training algorithms and fusion strategies.