Loading [a11y]/accessibility-menu.js
Improvements of the modified hypermap architecture for speech recognition | IEEE Conference Publication | IEEE Xplore

Improvements of the modified hypermap architecture for speech recognition


Abstract:

We are successfully using a coupled modeling concept which is suitable to reproduce sensory systems in a plausible way. The idea was to connect a biological relevant neur...Show More

Abstract:

We are successfully using a coupled modeling concept which is suitable to reproduce sensory systems in a plausible way. The idea was to connect a biological relevant neural network as a filter with a modified hypermap architecture (introduced by Kohonen) to classify the filtered data. The biological filter has the capacity to make segmentation and feature extraction of input data like a sensory pathway. Thus temporal processes can be represented in a sequence of prefiltered segments. The produced time sequences are suited for the analysis by a multistage construction of the modified hypermap architecture. In this paper we present a further improvement of our modified hypermap architecture, the a priori knowledge learning algorithm. The presented system is successfully used for spoken speech recognition of different subjects.
Date of Conference: 27 November 1995 - 01 December 1995
Date Added to IEEE Xplore: 06 August 2002
Print ISBN:0-7803-2768-3
Conference Location: Perth, WA, Australia
Federal Institute for Neurobiology Magdeburg, Magdeburg, Germany
Federal Institute for Neurobiology Magdeburg, Magdeburg, Germany
Federal Institute for Neurobiology Magdeburg, Magdeburg, Germany

Federal Institute for Neurobiology Magdeburg, Magdeburg, Germany
Federal Institute for Neurobiology Magdeburg, Magdeburg, Germany
Federal Institute for Neurobiology Magdeburg, Magdeburg, Germany

References

References is not available for this document.