Abstract
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.
Chapter PDF
References
Hermansky, H., Ellis, D.P.W., Sharma, S.: Tandem connectionist feature extraction for conventional HMM systems. In: Proceedings of the ICASSP 2000, vol. 3, pp. 1635–1638 (2000)
Gerber, M., Beutler, R., Pfister, B.: Quasi text-independent speaker verification based on pattern matching. In: ISCA. Proceedings of Interspeech 2007, pp. 1993–1996 (2007)
Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd edn. Prentice-Hall, Englewood Cliffs (1999)
Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification. Wiley Interscience, Chichester (2001)
Niesen, U., Pfister, B.: Speaker verification by means of ANNs. In: Proceedings of ESANN 2004, Bruges (Belgium), pp. 145–150 (2004)
Gerber, M., Pfister, B.: Quasi text-independent speaker verification with neural networks. MLMI 2005, Edinburgh (United Kingdom) (July 2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gerber, M., Kaufmann, T., Pfister, B. (2007). Perceptron-Based Class Verification. In: Chetouani, M., Hussain, A., Gas, B., Milgram, M., Zarader, JL. (eds) Advances in Nonlinear Speech Processing. NOLISP 2007. Lecture Notes in Computer Science(), vol 4885. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-77347-4_9
Download citation
DOI: https://doi.org/10.1007/978-3-540-77347-4_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-77346-7
Online ISBN: 978-3-540-77347-4
eBook Packages: Computer ScienceComputer Science (R0)