Acoustic Event Detection with MobileNet and 1D-Convolutional Neural Network

Pooi Shiang Tan, Kian Ming Lim, Chin Poo Lee, Cheah Heng Tan

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

5 Citations (Scopus)

Abstract

Sound waves are a form of energy produced by a vibrating object that travels through the medium that can be heard. Generally, the sound is used in human communication, music, alert, and so on. Furthermore, it also helps us to understand what are the events that occurring in the moment, and thereby, provide us hints to understand what is happening around us. This has prompt researchers to study on how humans understand what event is occurring based on the sound waves. In recent years, researchers also study on how to equip the machine with this ability, i.e. acoustic event detection. This study focuses on the acoustic event detection which leverage both frequency spectrogram technique and deep learning methods. Initially, a spectrogram image is generated from the acoustic data by using the frequency spectrogram technique. Then, the generated frequency spectrogram is fed into a pre-trained MobileNet model to extract robust features representations. In this work, 1 Dimensional Convolutional Neural Network (1D-CNN) is adopted to train a model for acoustic event detection. The feature representations are extracted from a pre-trained MobileNet. The proposed 1D-CNN consist of several alternatives of convolution and pooling layers. The last pooling layer is flattened and fed into a fully connected layer to classify the events. Dropout is employed to prevent overfitting. The proposed frequency spectrogram with pre-trained MobileNet and 1D-CNN is then evaluated with three datasets, which are Soundscapes1, Soundscapes2, and UrbanSound8k. From the experimental results, the proposed method obtained 81, 86, and 70 F1-score, for Soundscapes1, Soundscapes2, and UrbanSound8k, respectively.

Original languageEnglish
Title of host publicationIEEE International Conference on Artificial Intelligence in Engineering and Technology, IICAIET 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728169460
DOIs
Publication statusPublished - 26 Sept 2020
Externally publishedYes
Event2020 IEEE International Conference on Artificial Intelligence in Engineering and Technology, IICAIET 2020 - Kota Kinabalu, Sabah, Malaysia
Duration: 26 Sept 202027 Sept 2020

Publication series

NameIEEE International Conference on Artificial Intelligence in Engineering and Technology, IICAIET 2020

Conference

Conference2020 IEEE International Conference on Artificial Intelligence in Engineering and Technology, IICAIET 2020
Country/TerritoryMalaysia
CityKota Kinabalu, Sabah
Period26/09/2027/09/20

Keywords

  • 1D convolutional neural network
  • Acoustic event detection
  • frequency spectrogram
  • MobileNet

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Information Systems and Management
  • Instrumentation

Fingerprint

Dive into the research topics of 'Acoustic Event Detection with MobileNet and 1D-Convolutional Neural Network'. Together they form a unique fingerprint.

Cite this