Acoustic Scene Analysis and Classification Using Densenet Convolutional Neural Network

EasyChair Preprint 8056

Abstract

In this paper we present an account of state-of the-art in Acoustic Scene Classification (ASC), the task of environmental scenario classification through the sounds they produce. Our work aims to classify 50 different outdoor and indoor scenario using environmental sounds. We use a dataset ESC-50 from the IEEE challenge on Detection and Classification of Acoustic Scenes and Events (DCASE). In this we propose to use 2000 different environmental audio recordings. In this method the raw audio data is converted into Mel-spectrogram and other characteristics like Tonnetz, Chroma and MFCC. The generated Mel-spectrogram is fed as an input to neural network for training. Our model follows structure of neural network in the form of convolution and pooling. With a focus on real time environmental classification and to overcome the problem of low generalization in the model, the paper introduced augmentation to achieve modified noise based audio by adding gaussian white noise. Active researches are going on, in the audio domain and we have seen a lot of progress in the past years.

Keyphrases: ASC, Augmentation, CNN, Convolutional Neural Network, DenseNet, MFCC, Mel-spectrogram, ReLU Activation Function, Tonnetz, audio classification, chroma, deep learning

@booklet{EasyChair:8056,
  author    = {Samyak Doshi and Tushar Patidar and Shubhankar Gautam and Rajkishor Kumar},
  title     = {Acoustic Scene Analysis and Classification Using Densenet Convolutional Neural Network},
  howpublished = {EasyChair Preprint 8056},
  year      = {EasyChair, 2022}}