Fuzzy variants of hard classification rules for speech pattern recognition in Romanian language

The paper presents results obtained in a vowel recognition task applying unsupervised and supervised fuzzy algorithms and fuzzy neural networks. The vowels, uttered from 10 speakers each in 1000 different contexts are recognized using as features the first three formant frequencies. Feature extraction is presented and two fuzzy algorithms, fuzzy ISODATA and fuzzy k-NN, and the fuzzy multilayer perceptron neural network used for recognition are given. Conclusions about the obtained results with future plans and a reference list close the paper.