Determination of input parameters of the neural network model, intended for phoneme recognition of a voice signal in the systems of distance learning

Abstract

The article is devoted to the problem of voice
signals recognition means introduction in the system of distance
learning. The results of the conducted research determine the
prospects of neural network means of phoneme recognition.
It is also shown that the main diculties of creation of the
neural network model, intended for recognition of phonemes
in the system of distance learning, are connected with the
uncertain duration of a phoneme-like element. Due to this
reason for recognition of phonemes, it is impossible to use
the most eective type of neural network model on the basis
of a multilayered perceptron, at which the number of input
parameters is a xed value. To mitigate this shortcoming, the
procedure, allowing to transform the non-stationary digitized
voice signal to the xed quantity of mel-cepstral coecients,
which are the basis for calculation of input parameters of
the neural network model, is developed. In contrast to the
known ones, the possibility of linear scaling of phoneme-
like elements is available in the procedure. The number of
computer experiments conrmed expediency of the fact that
the use of the oered coding procedure of input parameters
provides the acceptable accuracy of neural network recognition
of phonemes under near-natural conditions of the distance
learning system. Moreover, the prospects of further research in
the eld of development of neural network means of phoneme
recognition of a voice signal in the system of distance learning
is connected with an increase in admissible noise level. Besides,
the adaptation of the oered procedure to various natural
languages, as well as to other applied tasks, for instance, a
problem of biometric authentication in the banking sector, is
also of great interest.