Acoustic-Based Emergency Vehicle Detection Using Convolutional Neural Networks
This work investigates how to detect emergency vehicles such as ambulances, fire engines, and police cars based on their siren sounds. Recognizing that car drivers may sometimes be unaware of the siren warnings from the emergency vehicles, especially when in-vehicle audio systems are used, we propos...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9072379/ |
| _version_ | 1818427968353992704 |
|---|---|
| author | Van-Thuan Tran Wei-Ho Tsai |
| author_facet | Van-Thuan Tran Wei-Ho Tsai |
| author_sort | Van-Thuan Tran |
| collection | DOAJ |
| description | This work investigates how to detect emergency vehicles such as ambulances, fire engines, and police cars based on their siren sounds. Recognizing that car drivers may sometimes be unaware of the siren warnings from the emergency vehicles, especially when in-vehicle audio systems are used, we propose to develop an automatic detection system that determines whether there are siren sounds from emergency vehicles nearby to alert other vehicles' drivers to pay attention. A convolutional neural network (CNN)-based ensemble model (SirenNet) with two network streams is designed to classify sounds of traffic soundscape to siren sounds, vehicle horns, and noise, in which the first stream (WaveNet) directly processes raw waveform, and the second one (MLNet) works with a combined feature formed by MFCC (Mel-frequency cepstral coefficients) and log-mel spectrogram. Our experiments conducted on a diverse dataset show that the raw data can complement the MFCC and log-mel features to achieve a promising accuracy of 98.24% in the siren sound detection. In addition, the proposed system can work very well with variable input length. Even for short samples of 0.25 seconds, the system still achieves a high accuracy of 96.89%. The proposed system could be helpful for not only drivers but also autopilot systems. |
| first_indexed | 2024-12-14T14:54:09Z |
| format | Article |
| id | doaj.art-5080316787ee43de91bdb588704ad98f |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T14:54:09Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-5080316787ee43de91bdb588704ad98f2022-12-21T22:57:02ZengIEEEIEEE Access2169-35362020-01-018757027571310.1109/ACCESS.2020.29889869072379Acoustic-Based Emergency Vehicle Detection Using Convolutional Neural NetworksVan-Thuan Tran0https://orcid.org/0000-0002-3197-679XWei-Ho Tsai1National Taipei University of Technology, Taipei, TaiwanNational Taipei University of Technology, Taipei, TaiwanThis work investigates how to detect emergency vehicles such as ambulances, fire engines, and police cars based on their siren sounds. Recognizing that car drivers may sometimes be unaware of the siren warnings from the emergency vehicles, especially when in-vehicle audio systems are used, we propose to develop an automatic detection system that determines whether there are siren sounds from emergency vehicles nearby to alert other vehicles' drivers to pay attention. A convolutional neural network (CNN)-based ensemble model (SirenNet) with two network streams is designed to classify sounds of traffic soundscape to siren sounds, vehicle horns, and noise, in which the first stream (WaveNet) directly processes raw waveform, and the second one (MLNet) works with a combined feature formed by MFCC (Mel-frequency cepstral coefficients) and log-mel spectrogram. Our experiments conducted on a diverse dataset show that the raw data can complement the MFCC and log-mel features to achieve a promising accuracy of 98.24% in the siren sound detection. In addition, the proposed system can work very well with variable input length. Even for short samples of 0.25 seconds, the system still achieves a high accuracy of 96.89%. The proposed system could be helpful for not only drivers but also autopilot systems.https://ieeexplore.ieee.org/document/9072379/Audio recognitionconvolutional neural networksemergency vehicle detectionsiren sounds |
| spellingShingle | Van-Thuan Tran Wei-Ho Tsai Acoustic-Based Emergency Vehicle Detection Using Convolutional Neural Networks IEEE Access Audio recognition convolutional neural networks emergency vehicle detection siren sounds |
| title | Acoustic-Based Emergency Vehicle Detection Using Convolutional Neural Networks |
| title_full | Acoustic-Based Emergency Vehicle Detection Using Convolutional Neural Networks |
| title_fullStr | Acoustic-Based Emergency Vehicle Detection Using Convolutional Neural Networks |
| title_full_unstemmed | Acoustic-Based Emergency Vehicle Detection Using Convolutional Neural Networks |
| title_short | Acoustic-Based Emergency Vehicle Detection Using Convolutional Neural Networks |
| title_sort | acoustic based emergency vehicle detection using convolutional neural networks |
| topic | Audio recognition convolutional neural networks emergency vehicle detection siren sounds |
| url | https://ieeexplore.ieee.org/document/9072379/ |
| work_keys_str_mv | AT vanthuantran acousticbasedemergencyvehicledetectionusingconvolutionalneuralnetworks AT weihotsai acousticbasedemergencyvehicledetectionusingconvolutionalneuralnetworks |