Badura Stefan
Lieskovsky Anton
This paper proposes a novel approach for speech recognition from sound. The most existing systems used in the task of sound recognition utilize a kind of neural network or hidden Markov models as classifiers. Our model presents a hierarchical structure of layers, where each layer is contextually dependent. We expand network design where fuzzy combinational networks with fuzzy flip-flops’ memories are combined and which we have described earlier. Experiments with fuzzy flip-flop network propose a new approach in the process of automatic speech recognition system for simple input entities - vowels.
Keywords – speech recognition, fuzzy logic, flip-flop, neural network, memory, combinatorial circuits