Design and implementation of voice command using MFCC and HMMs method

The more frequent human interaction to technology demands the development of methods of interaction with the machine to a more natural. Sound which is the most frequently used communication humans makes it one of the natural methods of interaction. Thus the development of a system that can recognize human speech as an action on the machine can be an option for those problems. Voice command is a speech recognition system to give the functions and actions on a system that has been defined as Command and Control systems. Amplitude value is taken from the input sound signal, so we get a set of real numbers is the value input for feature extraction. Feature extraction methods used in this paper are Mel frequency cepstral coefficient (MFCC). Early stages of MFCC is splitting the input signal amplitude values into frames which are processed using the mel-filterbak adapted from the human hearing system. The results of feature extraction made into a codebook which is used as an input symbol on HMM to form a model of every word. On testing step the characteristics of the test signal that has been quantized, then matched with the model that has been created in the previous step. From the test results, the system can recognize spoken words of speakers with an average accuracy of 93.89% in the environment without noise, and 58.1% in environments with noise.