Recognition of car horns based on principal component analysis of MEL frequency Cepstral coefficients and support vector machine

Abstract

With the rapid increase in the number of automobiles, the noise pollution caused by car horns is attracting more attention. In order to accurately identify car horn sounds in traffic noise and strengthen traffic law enforcement, research on car horn sound recognition is becoming increasingly important. In this paper, using Principal Component Analysis (PCA) to optimize and reduce the dimensionality of extracted Mel Frequency Cepstral Coefficients (MFCC), feature vectors are input into four models: Support Vector Machine (SVM), Back Propagation (BP) Neural Network, Extreme Learning Machine (ELM), and Random Forest (RF). These models are utilized to classify and identify car horn sounds from traffic noise. The impact of feature dimensions and Signal-to-noise ratio(SNR) on recognition performance is analyzed. The results show that under this method, the recognition rates of the four models can be increased by increasing the number of Mel filters and feature dimensions in MFCC, which can improve recognition performance, especially when the SNR is lower. The SVM model exhibits the most significant improvement in recognition rate. They achieve the best recognition rates for measured car horn sounds of 98.66 %, 93.98 %, 89.44 %, and 95.12 %, respectively. Experimental results demonstrate that the proposed method has good recognition performance and can be effectively applied to the supervision of car horn usage on actual roads.