Abstract: The voice recognition is the method that calculates an optimal match between two given sequences with certain restrictions is called Dynamic time wrapping. The sequences are "warped" non-linearly in the time dimension to determine a measure of their similarity independent of certain non-linear variations in the time dimension. This sequence alignment method is often used in time series classification. Although DTW measures a distance-like quantity between two given sequences, it doesn't guarantee the triangle inequality to hold. The voice recognition is the ability of a machine to recognize the spoken words and convert them to any desired form. In the current scenario when we are moving towards the automated world, the applications of real-time voice recognition are increasing day by day. The voice recognition system is a good choice to give a voice command for any device which requires user inputs to operate. Lifts, television, gaming-stations, smart-phones and medical instruments are the few of the many such examples. The real time voice recognition system first requires some training and then is ready to recognize the real time voice data input. For a new incoming voice command, the system tries to match its features from the existing data set. The command is then classified into the ‘best-matched’ command from the existing data set. The technological advancement in the field of pattern recognition had made the voice recognition more reliable and user friendly.
Keywords: Mel-frequency cepstral coefficient (MFCC), Short time energy, Zero crossing Rate, Power spectral density, Dynamic time wrapping etc.
Title: SPEECH RECOGNITION AND ELIMINATION THE NOISE BASED ON MFCC
Author: Karan Singh, Anil Bajaj, Rekha Garg
International Journal of Engineering Research and Reviews
ISSN 2348-697X (Online)
Research Publish Journals
