Spoken Handwriting for User Authentication using Joint Modelling Systems
| Type of publication: | Inproceedings |
| Citation: | humm09:ispa |
| Booktitle: | Proceedings of the 6th International Symposium on Image and Signal Processing and Analysis (ISPA 09), Salzburg, Austria, September 16 - 18 |
| Year: | 2009 |
| URL: | http://www.hennebert.org/downl... |
| Abstract: | We report on results obtained with a new user authentication system based on a combined acquisition of online pen and speech signals. In our approach, the two modalities are recorded by simply asking the user to say what she or he is simultaneously writing. The main benefit of this methodology lies in the simultaneous acquisition of two sources of biometric information with a better accuracy at no extra cost in terms of time or inconvenience. Another benefit comes from an increased difficulty for forgers willing to perform imitation attacks as two signals need to be reproduced. Our first strategy was to model independently both streams of data and to perform a fusion at the score level using state-of-the-art modelling tools and training algorithms. We report here on a second strategy, complementing the first one and aiming at modelling both streams of data jointly. This approach uses a recognition system to compute the forced alignment of Hidden Markov Models (HMMs). The system then tries to determine synchronization patterns using these two alignments of handwriting and speech and computes a new score according to these patterns. In this paper, we present these authentication systems with the focus on the joint modelling. The evaluation is performed on MyIDea, a realistic multimodal biometric database. Results show that a combination of the different modelling strategies (independent and joint) can improve the system performance on spoken handwriting data. |
| Keywords: | Biometrics, GMM, Speaker Verification, Writer Verification |
| Authors | |
| Added by: | [] |
| Total mark: | 0 |
|
Attachments
|
|
|
Notes
|
|
|
|
|
|
Topics
|
|
|
|
|