Abstract

Hearing is a very important sensory function for humans. Deaf people who fail to recognize signals indicating dangerous situations around them can endanger their lives, such as building fire alarm signals, gas leak alarms, tsunami alarms, and other dangerous alarms. This research proposes a tool system that can recognize and classify alarm sounds automatically. The two deep learning models we propose for the alarm sound classification task are CNN (Convolutional Neural Network) and LSTM (Long Short Term Memory). The models are trained by using the Mel-Spectrogram extracted from the alarm audio dataset. Based on this experiment, CNN gets better accuracy, reaching 98.83% while the accuracy of the LSTM model is 96.66%. Then the best model will be deployed to the Raspberry Pi, which uses a low-cost microphone for real-time applications.

Original languageEnglish
Title of host publication2022 International Conference of Science and Information Technology in Smart Administration, ICSINTESA 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages133-138
Number of pages6
ISBN (Electronic)9781665472883
DOIs
Publication statusPublished - 2022
Event2022 International Conference of Science and Information Technology in Smart Administration, ICSINTESA 2022 - Virtual, Online, Indonesia
Duration: 10 Nov 202212 Nov 2022

Publication series

Name2022 International Conference of Science and Information Technology in Smart Administration, ICSINTESA 2022

Conference

Conference2022 International Conference of Science and Information Technology in Smart Administration, ICSINTESA 2022
Country/TerritoryIndonesia
CityVirtual, Online
Period10/11/2212/11/22

Keywords

  • CNN
  • LSTM
  • Raspberry Pi
  • alarm
  • automatic
  • classification
  • deaf
  • deep learning
  • real-time

Fingerprint

Dive into the research topics of 'Automatic Sound Alarm Classification Using Deep Learning For the Deaf and Hard of Hearing'. Together they form a unique fingerprint.

Cite this