= Sound event detector

SED (Sound Event Detector) is a solution that uses a proprietary algorithm driven by machine learning technology to detect, classify and subsequently alert on unwanted acoustic events. These events can be a gunshot, a scream, or high urban noise levels.

The SED has exceptional accuracy that provides the confidence to address threats quickly and avoid wasting resources on false alarms. In addition, this solution enables sound detection to operate on devices with low-power, low-cost processors.

SED makes the world safer, a sound at the time.

SED save the average response time of rescue services from 7 minutes to less than 5 seconds. Helps to save more lives.

Every second matters

Functional diagram

The SED analyzes the common background sounds from the environment in which it is located and adapts. 

Step 0: Adaptation

The SED analyzes the common background sounds from the environment in which it is located and adapts. 

The SED detects an unwanted sound event that is atypical in the environment. 

 

Step 1: Detection

The SED detects an unwanted sound event that is atypical in the environment. 

The SED analyzes the common background sounds from the environment in which it is located and adapts. 

Step 2: Extraction

The SED processes the input audio signal and extracts the audio features used to train the classifier.

The SED classifies the sound event and recognizes whether it falls into one of the undesired categories.

Step 3: Classification

The SED classifies the sound event and recognizes whether it falls into one of the undesired categories. 

The SED triggers an alarm if the event is evaluated as undesirable. 

Step 4: Result

The SED triggers an alarm if the event is evaluated as undesirable. 

The SED informs the user about the event, and help can be on the way immediately.

Step 5: Notification

The SED informs the user about the event, and help can be on the way immediately.

 

Immediate response saves lives.

The average processing time of a human reaction when evaluating a dangerous situation is around 7 minutes. The SED processing time is measured in seconds. This time can be crucial.

Solutions

Software solution

SED’s SW solution is powered by state-of-the-art machine learning techniques with optimized deep neural network architectures running on low-power MCUs in real-time.

The software has been developed with an emphasis on speed and efficiency and allows third parties to easily adapt it to their embedded (low power) hardware platforms. The solution comes with a very intuitive user application, and both products can be customized to suit your needs.

It’s not a problem if you don’t want integration into your product; we also have our own devices ready for immediate order!

Hardware solution

Our SED device is ready to operate in both indoor and outdoor situations. The integrated GSM/GPRS module ensures operability anywhere where the network is available and requires minimum data.

The software solution and user application come fully integrated and ready for immediate use to provide all the information from connected devices in real-time.

About us

JALUD Embedded

JALUD Embedded is a tech innovative company that specializes in creating 32-bit Embedded solutions and specific mobile applications and integrating their solutions. We develop solutions independent of the operating system.

The company’s mission is to minimize the consequences of dangerous events, to contribute to saving property, health and life of people.

Main benefits of SED

Real-time monitoring and Quick reaction time

The average processing time of a human reaction when evaluating a dangerous situation is around 7 minutes; with the SED solution, the processing time is 2 seconds allowing it to help save more lives.

Our solutions provide you with real-time alerts that can be sent to mobile or desktop applications.

Cost-effective

The SED saves the average response time of rescue and increases the efficiency of security teams, saving money on the human resources required to monitor all the cameras needed in your surveillance center.

The installation process is simpler, as it does not require any infrastructure, and you can get coverage from remote locations thanks to the integrated GSM and a battery version device (battery or solar-powered).

GDPR compliant

No sound is recorded, therefore avoiding ethical concerns and keeping people’s privacy. We are 100% GDPR compliant.

Scene location

When at least three devices detect the same hazardous situation, the exact location of the sound source is triangulated and displayed to the user. The location is updated as the following dangerous sounds are detected.

Quality of life

Security of the citizen. SED can measure loudness in its surroundings and keep track of the urban noise (noise pollution).

Frequently asked questions

Our servers are used only for forwarding meta-data to client, they are located in Italy and Czech Republic. 

Yes and no, the solutions don’t recognize words. They are trained to detect and alert specific impulsive sounds, not voice recognition. However, when shouting words during a “panic screaming”, words such as “help” are recognized and operator gets notified.

You require three devices to be able to triangulate an event.

Bomb blasting: +400m, Gunshot: +250m, Human scream: +150m, Glass breaking: +60m

Yes, we enable the integration of sending events from the device into a third-party software solution. Integration can be sone to all software platforms that provide access over an open API interface.

Unlimited devices can be connected to the same account.

Get in touch

We will be more than happy to assist. If you’re interested in our sound detector, we can call or meet and discuss all the benefits we’re sure our solution can provide to you!

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply, same as our own Privacy Policy.