A PATTERN RECOGNITION APPROACH TO ROBUST VOICED/UNVOICED SPEECH CLASSIFICATION USING FUZZY LOGIC

Abstract

In the field of mobile communications new robust Voiced/Unvoiced (V/UV) classification algorithms are required in that correct voicing detection is a crucial point in the perceived quality and naturalness of a very low bit-rate speech coding system. The paper shows that a valid and more convenient alternative to deal with the problem of voicing decision is to use methodologies like fuzzy logic which are suitable for problems requiring approximate rather than exact solutions, and which can be represented through descriptive or qualitative expressions. The Fuzzy Voicing Detector proposed is based on a pattern recognition approach in which the matching phase is performed using three fuzzy rules. The rules have been obtained using FuGeNeSys, a new hybrid learning tool based on Genetic Algorithm and Neural Networks. The fuzzy classifier is computationally very simple and more efficient than traditional methods, which are affected by misclassification errors, above all in the presence of background noise.