Control of Electronic Devices Using Neural Network Based Sundanese Speech Recognition

This paper describes how speech recognition automatically uses the local language that originated from Indonesia, namely the Sundanese, which can control electronic devices in the home. Sundanese is the second most widely used regional language in Indonesia after Java. Voice recognition using Sundanese is carried out in this study to be able to control several electronic devices directly with high accuracy. The method used in the introduction of Sundanese is the Mel Frequency Cepstral Coefficient (MFCC) extraction method and identification of backpropagation-based neural networks. There are 10 Sundanese instructions used in the introduction to speech as input to the system, and each instruction has 2 to 3 Sundanese syllables. The output used by the author in this paper is five household electronic devices, to turn on or turn off controlled output using 2 Sundanese instructions. The data used in the backpropagation training process is 300 data; each instruction is 30 data. The results of training weights can produce an accuracy rate of 96.7% when testing the system. The control system uses the MFCC method and artificial neural network backpropagation algorithm so that the program works and Sundanese language voice recognition is good.