MFCC HMM SYSTEM AND METHOD FOR HIDDEN MARKOV MODEL BASED UAV SOUND RECOGNITION USING MFCC TECHNIQUE IN PRACTICAL NOISY ENVIRONMENTS

摘要

Disclosed are a method for recognizing an unmanned aerial vehicle (UAV) sound based on a hidden Markov model (HMM) using a mel-frequency cepstral coefficients (MFCC) technique in an environment having much real noise and a system thereof. A method for recognizing sound of a UAV comprises the following steps of: extracting a feature vector related to a sound signal of a UAV based on an MFCC technique in an environment where noise exists; training an HMM model based on a training data set generated based on the extracted feature vector; and recognizing a sound signal corresponding to the UAV based on the trained HMM model with respect to an input sound signal.