ITRW on Non-Linear Speech Processing (NOLISP 07) Paris, France May 22-25, 2007

Perceptron-based Class Verification

Michael Gerber, Tobias Kaufmann, Beat Pfister

Speech Processing Group, Computer Engineering and Networks Laboratory, ETH Zürich, Switzerland

We present a method to use multilayer perceptrons (MLPs) for a verification task, i.e. to verify whether two vectors are from the same class or not. In tests with synthetic data we could show that the verification MLPs are almost optimal from a Bayesian point of view. With speech data we have shown that verification MLPs generalize well such that they can be deployed as well for classes which were not seen during the training.

Full Paper

Bibliographic reference.  Gerber, Michael / Kaufmann, Tobias / Pfister, Beat (2007): "Perceptron-based class verification", In NOLISP-2007, 35-38.