Sound Classification Using Convolutional Neural Network and Tensor Deep Stacking Network

IEEE Access

Babita Pandey¹  Prayag Tiwari²  Nhu Gia Nguyen³  Ashish Khanna⁴  Deepak Gupta⁴  Aditya Khamparia⁵ 

[1] Department of Computer and Information Technology, Babasaheb Bhimrao Ambedkar University, Lucknow, India;Department of Information Engineering, University of Padova, Padua, Italy;Graduate School, Computer Science, Duy Tan University, Da Nang, Vietnam;Maharaja Agrasen Institute of Technology, New Delhi, India;School of Computer Science and Engineering, Lovely Professional University, Phagwara, India;

关键词: Deep learning;    convolutional neural network;    tensor deep stacking networks;    spectrograms;   

DOI  :  10.1109/ACCESS.2018.2888882

来源: DOAJ

【 摘 要 】

In every aspect of human life, sound plays an important role. From personal security to critical surveillance, sound is a key element to develop the automated systems for these fields. Few systems are already in the market, but their efficiency is a point of concern for their implementation in real-life scenarios. The learning capabilities of the deep learning architectures can be used to develop the sound classification systems to overcome efficiency issues of the traditional systems. Our aim, in this paper, is to use the deep learning networks for classifying the environmental sounds based on the generated spectrograms of these sounds. We used the spectrogram images of environmental sounds to train the convolutional neural network (CNN) and the tensor deep stacking network (TDSN). We used two datasets for our experiment: ESC-10 and ESC-50. Both systems were trained on these datasets, and the achieved accuracy was 77% and 49% in CNN and 56% in TDSN trained on the ESC-10. From this experiment, it is concluded that the proposed approach for sound classification using the spectrogram images of sounds can be efficiently used to develop the sound classification and recognition systems.

【 授权许可】

Unknown