Self-Organizing Maps For Identifying Impaired Speech

Abstract

This paper presents a method of identifying heavily impaired pronunciations of 'r' consonant in Romanian language using Kohonen neural networks. The study focused on words that contain 'r' as the first letter and used signals recorded mainly from children, as mispronunciations occur most of the time at young age persons. Parameters of the alternating component of each speech sample's envelope are used as feature vectors in the classification stage.

Keywords

• speech processing
• impaired speech evaluation
• self-organizing maps