Classifies the Input Sound Waves Using Neural Network and Sequence Learning Model

Classifies the Input Sound Waves in continuous speech is a tough task with a low accuracy rate. By using the sequence learning algorithm to add sequential information ofindividual phonemes, recognition performance can be improved. This thesis includes three parts. A self-organized neural network is the first part, which classifies the inputsound waves into forty-two different phoneme categories. The 42 output neurons of the neural network are sent to the Sequence Learning block which is composed of Long Term Memory cells. Finally, each LTM cell sends a unique feedback strength signal to each output of the neural network to forecast the next phoneme, hence, to improve theClassifies the Input Sound Waves based on the sequential information. It is the purpose of this thesis is to describe a biologically motivated approach for phoneme recognition by using a self-organized neural network and sequence learning algorithm.

کلیدواژه ها:

Sound Waves ، Neural Network ، Sequence Learning