Robust Sound Classification for Surveillance using Time Frequency Audio Features

Acoustic-Based Train Arrival Detection Using Convolutional Neural Networks With Attention

“…A-TAD broadly belongs to the audio classification problem which is also known as sound classification (SC), so prior works on SC can lay a good foundation for the development of A-TAD systems. Sound classification has recently received increasing research attention and applied in a wide variety of applications, such as surveillance [7], predictive maintenance [8], smart home security systems [9], emergency vehicle detection [10] [11], environmental sound classification (ESC) [12] [13] [14], and speech recognition [15]. The conventional solutions for sound classification include signal processing techniques and traditional machine learning methods, such as the Gaussian mixture model (GMM) [16] [17], support vector machine (SVM) [18], and hidden Markov model (HMM) [19].…”

Microphone Array Based Surveillance Audio Classification

“…In recent years, researchers have shown that the most effective tools for the classification of sound events include the application of deep, convolutional, and recurrent neural networks (DNN, CNN, and RNN) [7], [8], [3], [9], [4]. However, for the current work, the concern with the processing time of the algorithms is fundamental, since, among the future goals, the aim is to create a low-cost system capable of running in real-time.…”

“…[8], [3], [4] states that temporal and frequency features, when separately used, can't achieve satisfactory performance, especially in noisy environments, but the combination of those can significantly improve the classification task. The authors [8] and [4] claim that Spectral Chroma, Spectral Contrast, and Tonnetz were primarily related to musical classification, but examine their performance in classification of other sorts of audio signals, attesting they exert a fundamental role in that duty. In [8], [3], and [4], the authors confirm the excellent performance of MFCC and its first and second-order derivatives, Delta and Delta Delta.…”

“…The authors [8] and [4] claim that Spectral Chroma, Spectral Contrast, and Tonnetz were primarily related to musical classification, but examine their performance in classification of other sorts of audio signals, attesting they exert a fundamental role in that duty. In [8], [3], and [4], the authors confirm the excellent performance of MFCC and its first and second-order derivatives, Delta and Delta Delta.…”

“…In this sense, the monitoring of risk areas could be done through the use of audio processing techniques, reducing the need for human participation in the surveillance process, and making public security systems more efficient [4]. To support this argument, it is worth recalling two very favorable characteristics concerning these signals: initially, the sound consumes less bandwidth in the transmission of information, reducing the need for high transmission rates, as in the case of high definition images; in addition, sound processing techniques require, in general, less computational power than techniques for video processing and analysis, which would enable the implementation of simpler and therefore less costly embedded systems [3], [5].…”