A set of Multi-Layered Networks (MLN) for Automatic Speech Recognition (ASR) is proposed. Such a set allows to integrate information extracted with variable resolution in the lime and in the frequency domain and to keep the number of links between nodes of the networks small in order to allow significant generalization during learning with a reasonable training set size.
Speech Coding with Multilayer Networks
Contributo in volume
Springer-Verlag, Berlin/Heidelberg, DEU
Neuro-computing: algorithms, architectures, and applications, edited by Françoise Fogelman-Soulié, Jeanny Hérault, pp. 207–216. Berlin/Heidelberg: Springer-Verlag, 1990