A siren identification system using deep learning to aid hearing-impaired people

Arturo, Ramirez, Eugenio, Donati ORCID: https://orcid.org/0000-0002-0048-1858 and Christos, Chousidis ORCID: https://orcid.org/0000-0003-3762-8208 (2022) A siren identification system using deep learning to aid hearing-impaired people. Engineering Applications of Artificial Intelligence, 114. ISSN 0952-1976

[thumbnail of Ramirez_Donati_Chousidis_final_2_Rev_2.2.pdf]
Ramirez_Donati_Chousidis_final_2_Rev_2.2.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (1MB) | Preview


The research presented in this paper is aiming to address the safety issue that hearing-impaired people are facing when it comes to identifying a siren sound. For that purpose, a siren identification system, using deep learning, was designed, built, and tested. The system consists of a convolutional neural network that used image recognition techniques to identify the presence of a siren by converting the incoming sound into spectrograms. The problem with the lack of datasets for the training of the network was addressed by generating the appropriate data using a variety of siren sounds mixed with relevant environmental noise. A hardware interface was also developed to communicate the detection of a siren with the user, using visual methods. After training the model, the system was extensively tested using realistic scenarios to assess its performance. For the siren sounds that were used for training, the system achieved an accuracy of 98 per cent. For real-world siren sounds, recorded in the central streets of London, the system achieved an accuracy of 91 per cent. When it comes to the operation of the system in noisy environments, the tests showed that the system can identify the presence of siren when this is at a sound level of up to -6 db below the background noise. These results prove that the proposed system can be used as a base for the design of a siren-identification application for hearing-impaired people.

Item Type: Article
Identifier: 10.1016/j.engappai.2022.105000
Keywords: Siren, Siren detection, Real-time siren detection, Spectrograms, Deep learning for audio, Convolutional neural network, Embedded systems, Automobile safety, Road safety, Hearing-impaired people, Visual indication
Subjects: Construction and engineering > Electrical and electronic engineering
Computing > Intelligent systems
Related URLs:
Depositing User: Christos Chousidis
Date Deposited: 16 Jun 2022 09:05
Last Modified: 06 Feb 2024 16:10
URI: https://repository.uwl.ac.uk/id/eprint/9159


Downloads per month over past year

Actions (login required)

View Item View Item