Retrieval of phonemes and Kohonen algorithm

TL;DR

This paper introduces a phoneme retrieval method using a neural network constructed with a set of neurons corresponding to typical data structures, aiming to improve voice and image recognition tasks.

Contribution

It proposes a novel network construction approach tailored for phoneme and image retrieval, addressing limitations of data dependency in traditional methods.

Findings

Effective phoneme retrieval demonstrated for voice recognition.

Network adapts to specific data sets like images or commands.

Improved recognition accuracy for targeted data sets.

Abstract

A phoneme-retrieval technique is proposed, which is due to the particular way of the construction of the network. An initial set of neurons is given. The number of these neurons is approximately equal to the number of typical structures of the data. For example if the network is built for voice retrieval then the number of neurons must be equal to the number of characteristic phonemes of the alphabet of the language spoken by the social group to which the particular person belongs. Usually this task is very complicated and the network can depend critically on the samples used for the learning. If the network is built for image retrieval then it works only if the data to be retrieved belong to a particular set of images. If the network is built for voice recognition it works only for some particular set of words. A typical example is the words used for the flight of airplanes. For example a command like the "airplane should make a turn of 120 degrees towards the east" can be easily recognized by the network if a suitable learning procedure is used.