SED (Sound Event Detector) uses a proprietary algorithm driven by machine learning to detect, classify and subsequently alert you to unwanted acoustic events, such as a gunshot, scream, car accident, baby crying, explosion, or glass breakage.
SED save the average
response time of rescue
services from 7
to less than 5 seconds. Helps to safe more lives.
The SED analyzes the common background sounds from
the environment in which it is located and adapts.
The SED detects unwanted sound event that is atypical
in the environment.
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.
The SED triggers an alarm if the event is evaluated
The SED informs about the event and help can be on
the way immediately.
The SED analyzes the common background sounds from the environment in which it is located and adapts.
The SED detects unwanted sound event that is atypical in the environment.
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.
The SED triggers an alarm if the event is evaluated as undesirable.
The SED informs about the event and help can be on the way immediately.
The average processing time of a human reaction when
evaluating a dangerous situation is around 7 minutes. The SED processing time
is 2 seconds. This time can be crucial.
The SW solution is developed with high emphasis on speed,
efficiency and enable third parties to easily port it to their (low power)
embedded hardware platforms.
We worked very hard to get current state-of-the-art Machine
Learning techniques with optimized deep neural network architectures running on
low-power MCUs in a real time.
Our software comes with a very intuitive user application. Both, the software
and the application can be customised to fit your needs. In case you do not
want integration into your own product, it is not a problem, we also have our
own devices that are ready for your immediate order!
Our device is ready to
operate in both indoor and outdoor situations. It is designed to be
waterproof (IP-67) and can withstand extreme temperatures (-40°C - 70°C).
Our software solution comes
to you fully integrated and ready for immediate use.Integrated GSM/GPRS module
ensures operability anywhere where the network is available.
The user application also
comes with the device to provide all the information from connected devices in
JALUD Embedded specializes in building 32bit Embedded solutions, specific mobile applications and integrating these solutions. We develop solutions independent on Operating system.
We are a creative and innovative company offering the development of fast and reliable software applications, including the integration of hardware for all proposed solutions and requests, while also adapting the applicable drivers (on our custom board support package) for interaction with external periphery.
Quality and reliability of your embedded systems is supported by a team of highly skilled engineers with cutting-edge ideas and vast experience with modern technology.
Dont't worry if it doesn't work right.If everything did, you'd be out of a job
Me and Jakub founded the company back in 2014. Our goal since the beginning has been to create a product that will benefit from our 10 years of experience in machine learning and embedded development.With SED it turns out, that we have created a product that is not only innovative but also helps the world to be a safer place.
When I finished my PhD with a focus on Neural Networks and worked as researcher, I already knew that I like innovations, leading people and having the freedom in making the decisions. Simply because the wrong decisions comes back pretty fast and the good ones are rewarded. After many years working for a big international company, I have almost forgotten about what I like, until I have rediscovered it with JALUD Embedded.
It serves for a good purpose, the product does not infringe our privacy, it is innovative, enthusiastic developer that will join our team will use extensive SW and HW skills, experience a lot of fun with us and with the product itself.
Never say that something is impossible to make or there comes a fool who does not know that it is not possible to make and makes it.
Ever since I was a student, I've wanted to start an innovative technology company. I found a friend Lukáš and colleague with whom we complement each other perfectly and within JALUD Embedded we can capitalize on our knowledge and experience in the field of artificial intelligence, machine learning and embedded systems.
Building a functioning, flexible and innovative company with a friendly environment. I am filled with work on a product that has a deeper meaning and that makes the world a safer place.
The deteriorating security situation in the world is forcing people to give up their privacy more and more at the expense of security. SED offers an alternative that, thanks to artificial intelligence, increases security without in any way interfering with people's privacy.
We have two lives, and the second begins when we realize we only have one
The team, I felt a very natural connection with the team and got the feeling we can achieve great things together.
I love that the projects we are working on with Jalud Embedded are making the world a better and safer place.
SED takes a different approach to traditional surveillance. The fact that is 100% private and ethical makes an extremely valuable product when privacy keeps on become a bigger and bigger concern in our society.
Nothing is perfect, what seems like it is, will perish
I bring valuable experience from the private health sector. In healthcare, and especially in first aid, it's about time. What and where are the two main questions of IRS when it comes to life. These questions take valuable minutes that often decide life and death. The SED is able to detect critical events and reduce the response time of assistance. Working for Jalud Embedded helps save lives, which is my goal.
Flexibility, adaptation and growth opportunities, I have great colleagues from whom I learn things every day and teach me skills that help me improve at work. Since we are at the beginning, we are masters of our decisions.
Its future, the SED, is a device that can change the way we humans respond to individual threats. Position and approximate situation detection is exactly what rescue systems need to operate, the SED is able to deliver this information in a fraction of the time of the current method.
leave the place better than you find it.
an optimist and a dreamer, so I enjoy working with like-minded people that
believe that big things can be achieved.
development allows me to be creative on a daily basis, help our partners find
better solutions,w hile
meeting new people and making new relationships.
Security is a need for everybody and SED empowers people
by making the World a safer place. The benefits of SED can be enjoyed by
Czech Republic (Pilsen), the main distribution channel for Europe.
JALUD Embedded s.r.o.
+420 773 092 900 firstname.lastname@example.org
We have been using JALUD's
glass breaking detection solution for the past three years and we couldn't be
happier with it. We integrated their software into our devices and this
process took place to the satisfaction of both parties.
Therefore, we can not
recommend them enough.
Keep up the good work!
No, the algorithm is highly optimized for use in embedded devices. For our client requirements we tested the SW with STM32F7 CPU, memory requirements were around 250-300kB and time of classification within 600ms.
It depends on the model settings, but standard length that has proven to work the best is around 0.5s
Currently, we are using high precision deep learning techniques to process the sound signal. When we have enough sound data to train the classifier, we can analyze any type of impulsive sound event (such as car crash, bomb blast, gunshot, human screaming, baby cry and many others) .
No, the sound is processed directly on the device and sound events are not stored or further send to the cloud. Unlike cameras, our solution does not interfere with people's privacy.
The recognition quality is at a high level, but for some types of sounds (eg human screaming) a false alarm can be expected. Our clients usually install the SED together with the camera system, and therefore we are preparing a variant of the SED together with the camera module, which will ensure that you have a visual overview of the reported dangerous situation.
The whole cycle of event: from capturing the event, classification, waking up the GSM, sending the event to the server and handing over the event to the client takes between 2-4 s.
JALUD Embedded s.r.o.
Nepomucká 1355/261 CZ-326 00 PilsenCzech Republic
+420 773 092 900