The subject of this project came from a “real life” problem- people with hearing disabilities that can drive a car, but can't hear if an ambulance is coming towards them or if a missile alarm is on. This inability makes them a safety hazard both to themselves and to their surroundings, because they can accidentally cause a roadblock or even an accident.
Although sirens from different countries or even different continents sound familiar to us- we can easily understand it is an alarm even if we never heard it before, there isn't a uniform standard for sirens today, and there isn't an algorithm that can detect sirens from different countries.
In this Project we have implemented a generic algorithm for detection of sirens in noisy environments on Android Smartphone that was suggested by Yeshurun and Carmel (*). The algorithm is based on advanced methods of signal processing and Machine Learning, which can detect Emergency signals, regardless of their origin.
We optimized the algorithm for implementation on Android Smartphone.
[*] Dean Carmel, Ariel Yeshurun, Yair Moshe.”Detection of Alarm Sounds in Noisy Environments”. EUSIPCO,2017.