Improved low computational method for siren detection

Dobre, Robert Alexandru; Negrescu, Cristian; Stanomir, Dumitru

doi:10.1109/siitme.2017.8259916

Cited by 12 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At last, we compared the results of our work with that of several existing related works listed in the literature review section. Some works based on microcontrollers [11]- [13] and circuit design [14], [15] only reported the possibilities of siren detection systems, and they did not evaluate the system's accuracy on an extensive dataset. Thus, we only focused on the comparison with works based on machine learning or deep learning approaches.…”

Section: ) Results Of the Proposed Ensemble Model (Sirennet) And Anamentioning

confidence: 99%

“…Till now, there are only a few studies on the recognition of siren sounds, such as [4]- [15]. J. Liaw et al proposed to recognize the ambulance siren sound in Taiwan by the Longest Common Subsequence (LCS) [4].…”

Section: Related Workmentioning

confidence: 99%

“…There are several works based on microcontrollers [11]- [13] and hardware design [14], [15] for siren sound detection. In [11], the ambulance's siren sound could be detected by employing two times Fast Fourier Transform (FFT) on a dsPIC microcontroller.…”

Section: Related Workmentioning

confidence: 99%

“…Although we can quickly implement this algorithm on Texas Instrument TMS DSPs, it was concluded to be not foolproof and may result in false detection. R. Dobre et al [14], [15] proposed low-computational methods for siren detection based on analog electronics circuits. The authors used SPICE to simulate the initial design [14] and its improved version [15] of the circuit block used for siren detection.…”

Section: Related Workmentioning

confidence: 99%

“…R. Dobre et al [14], [15] proposed low-computational methods for siren detection based on analog electronics circuits. The authors used SPICE to simulate the initial design [14] and its improved version [15] of the circuit block used for siren detection. The circuits were tested with a siren signal using the SPICE simulator and showed success in detection.…”

Section: Related Workmentioning

confidence: 99%

See 4 more Smart Citations

Acoustic-Based Emergency Vehicle Detection Using Convolutional Neural Networks

Tran

Tsai

2020

IEEE Access

View full text Add to dashboard Cite

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. INDEX TERMS Audio recognition, convolutional neural networks, emergency vehicle detection, siren sounds.

show abstract

Section: ) Results Of the Proposed Ensemble Model (Sirennet) And Anamentioning

confidence: 99%