Urban Sound Classification Using Convolutional Neural Network and Long Short Term Memory Based on Multiple Features
Joy Krishan Das, Arka Ghosh, Abhijit Kumar Pal, Sumit Dutta, Amitabha Chakrabarty
Abstract
There are many sounds all around us and our brain can easily and clearly identify them. Furthermore, our brain processes the received sound signals continuously and provides us with relevant environmental knowledge. Although not up to the level of accuracy of the brain, there are some smart devices which can extract necessary information from an audio signal with the help of different algorithms. Over the years several models like the Convolutional Neural Network (CNN), Artificial Neural Network (ANN), Region-Convolutional Neural Network (R-CNN) and many machine learning techniques have been adopted to classify sound accurately and these have shown promising results in the recent years in distinguishing spectra-temporal pictures and different sound classes. The novelty of our research lies in showing that the long-short term memory (LSTM) shows a better result in classification accuracy compared to CNN for many features used. Moreover, we have tested the accuracy of the models based on different techniques such as augmentation and stacking of different spectral-features. In such a way it was possible with our LSTM model, to reach an accuracy of 98.81%, which is state-of-the-art performance on the UrbanSound8k dataset.