Abstract
The author shows that a Kohonen self-organizing network can be used to reduce the effects of errors in digital transmission of speech, Kohonen learning is used to cause the network nodes to mimic the input data distribution, while self-organization is used to arrange the nodes so as to reduce sensitivity to transmission errors. The number of bit substitutions that can be tolerated without unacceptable degradation of the speech signal is roughly doubled by this method. In contrast to other applications of self-organizing networks, in this case the dimensionality of the network is very much higher than that of the input data.

This publication has 6 references indexed in Scilit: