End-to-end environmental sound classification using a 1D convolutional neural network. (1st December 2019)

• Record Type: Journal Article
• Authors: Abdoli, Sajjad; Cardinal, Patrick; Lameiras Koerich, Alessandro
• Is Part Of: Expert systems with applications. Volume 136(2019)
• Page Start: 252
• Page End: 263
• Publication Date: 2019-12-01
• Subjects: Convolutional neural network -- Environmental sound classification -- Deep learning -- Gammatone filterbank; AI Air conditioner -- BC Between Class -- CA Car horn -- CH Children playing -- CST Chroma, Spectral contrast, Tonnetz -- CNN Convolution Neural Network -- CRP Cross Recurrence Plot -- DS Dempster Shafer -- DO Dog bark -- DR Drilling -- EN Engine -- GU Gun shot -- JA Jackhammer -- LMC LM, CST -- LM Log-Mel -- MFCC Mel-Frequency Cepstral Coefficients -- MC MFCC, CST -- SI Siren -- SKM Spherical K-Means -- ST Street music -- SVMs Support Vector Machines; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2019.06.040
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: A model based on deep learning for environmental sound classification is proposed. Model provides the trade-off between the audio length, accuracy and parameter space. Model omits the signal processing modules and learns representations from audio. Model has a small parameter space compared to other architectures in the literature. The frequency and magnitude responses of some of the learned filters are analyzed. Abstract: In this paper, we present an end-to-end approach for environmental sound classification based on a 1D Convolution Neural Network (CNN) that learns a representation directly from the audio signal. Several convolutional layers are used to capture the signal's fine time structure and learn diverse filters that are relevant to the classification task. The proposed approach can deal with audio signals of any length as it splits the signal into overlapped frames using a sliding window. Different architectures considering several input sizes are evaluated, including the initialization of the first convolutional layer with a Gammatone filterbank that models the human auditory filter response in the cochlea. The performance of the proposed end-to-end approach in classifying environmental sounds was assessed on the UrbanSound8k dataset and the experimental results have shown that it achieves 89% of mean accuracy. Therefore, the proposed approach outperforms most of the state-of-the-art approaches that use handcrafted features or 2D representations as input. Moreover, the proposed approach outperforms all approaches that use raw audio signal as input to the classifier. Furthermore, the proposed approach has a small number of parameters compared to other architectures found in the literature, which reduces the amount of data required for training.