Indonesian Alphabet Speech Recognition for Early Literacy using Convolutional Neural Network Approach

Abstract

Games are considered capable of being used as a learning medium that can help teachers to teach children how to pronounce the Indonesian alphabet in early literacy, we try to build one aspect of the game in this study. The approach we use is a speech recognition approach that uses the convolutional neural network method. The results of this study indicate that CNN can recognize speech, with input data is in the form of sound. We use the MFCC feature vector sound feature to make a 3-dimensional matrix of input sound into CNN input. We also use the Sequential CNN architecture made from a simple 10 layer neural network, which produces a model with a small size, approximately only about 6 MB, with high accuracy (84%) and an F-Measure of 0.91.

Convolution neural networks with hybrid feature extraction methods for classification of voice sound signals

“…The convolution neural network used in different types of sound classification tasks due to its ability to automatically learn from the dataset while training. In some of the cases the CNN used for feature extraction followed by the SVM for the classification in the domain of sound classification and in some other work the handcrafted features are used with CNN to classify the sound of marine animals [28]. Further the use of combining deep learning (using CNN) and shallow learning for the problem of sound recognition with MFCC approach as baseline for both [29].…”