New Restricted Boltzmann Machines and Deep Belief Networks for Audio Classification

Conference: Speech Communication - 14th ITG Conference
09/29/2021 - 10/01/2021 at online

Proceedings: ITG-Fb. 298: Speech Communication

Pages: 5Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Baggenstoss, Paul M. (Fraunhofer FKIE, Wachtberg, Germany)

In this paper, the deep belief network (DBN), made popular by Hinton in 2006, is re-vitalized using maximum entropy sampling distributions, their corresponding activation functions, and a new direct training approach based on classifier performance. It is shown in keyword classification experiments that the DBN can compete with state of the art classifiers, and using additive classifier combination, improves upon a state of the art deep neural network.