About the client
OtoSense Inc. is a US-based startup company that developed an AI-enabled sound recognition app: the system is able to learn and then recognize sounds (acoustic vibrations), with several use cases including anomaly detection and preventive maintenance (early diagnostic).
OtoSense is a specialist in automatic sound recognition and leverages deep learning for that purpose. OtoSense has deployed different types of edge devices from circuit boards to be used in industrial environments (machine health) to mobile (Android, iOS) applications to improve the security and independence of people with hearing loss.
The OtoSense sound recognition app is used on ground and airborne vehicles as well as on critical industrial assets, in challenging environments where safety, scalability, and reliability are not optional: power plants, car body manufacturers, HVAC assembly lines, and in airport escalators, moving walkways and elevators. Major plane makers are using it for flight tests and airlines are using it to perform quick maintenance checks on the tarmac.
In 2018, Analog Devices acquired OtoSense. To this day, the Pentalog team continues to support OtoSense and is expected to keep doing so in the context of the acquisition by Analog.
The OtoSense start-up initiated its journey from considering there are 466 million people worldwide diagnosed with some level of hearing loss and that 95% of people with hearing impairment in developed countries are using mobile applications to support their activities on a daily basis.
With a vision to improve people’s lives, they started working on a sound source identification solution that would convert meaningful sounds at the workplace (think fire alarms, door bells) into animated visuals.
This was the time when Pentalog and OtoSense first came together in 2014 in Boston, before the company moved to Silicon Valley.
After the first product was released (an iOS app), OtoSense developed an AI engine able to learn more sounds, which could be deployed as a general automatic sound recognition system.
Do you want to build a similar project?
The first product developed by the team is called OtoSense, based on a technology called SIR, for Sound Intelligent Recognition.
OtoSense is a sound recognition app running on various mobile platforms. It records and analyzes background sounds and sends notifications to its user if any noticeable sound is recognized (fire alarm, doorbell, etc.). It also allows users to record specific sounds they want to be noticed about. The product’s specific user interface is adapted to people who might as well suffer from visual disorders.
How does this technology work?
Alike many AI-based systems, the OtoSense sound recognition app has two main components:
- The AI engine which implements different techniques from signal processing to deep learning algorithms and that may be trained to learn about sounds to recognize (alarm, baby crying, engine wearing off, house sounds, etc);
- The edge devices that process chunks of noise, extract the sound features of interest, and trigger alarms in the form of visuals, emails, SMS, notifications, etc. The edge devices may be either smartphones/tablets (iOS, Android), wearables such as smartwatches, electronic boards (e.g. Raspberry PI), or web applications.
OtoSense is an innovative solution, far more efficient and less expensive than the preceding systems.
Pentalog set up a dedicated team of 5 engineers based in Chisinau (Moldova) to support the development of the solution. They first worked on the improvement of the first prototype and then took over the development of the iOS and Android versions of the application, and its connection with the Pebble smartwatch.
The client’s next project consists of a global automatic sound recognition system combining the best of signal processing and deep learning techniques to serve both individuals (e.g. acoustic alarms detection and transformation into visual elements for individuals with impaired hearing capabilities) and companies looking to leverage automatic sound recognition for preventive maintenance and machine health improvement.
OtoSense is pleased with the Pentalog collaboration which started in 2014. Pentalog dedicated teams continue to support OtoSense teams in the development of new projects.
Key success factors:
- A high level of flexibility and efficiency due to the Scrum organization led by a senior Scrum Master
- A strong, solid, and proactive team that proposed many improvements which included a senior developer with a strong background in algorithms related to signal recognition
- A good alternative to expensive local resources
Sébastien Christian, Founder & CEO of OtoSense, stated that at Pentalog he found “the right team” to build his system: “a stable, robust, and solid team of developers, with a good head”. “The head of the team understands the software but beyond that, the algorithms behind.”
For the Pentalog team, this project has also been a great experience, because they’ve had the chance to discover new SDKs and new APIs in this growing world of the Internet of Things.
Our skilled developers with experience on similar projects
Otosense - A stable, robust and solid team of developers, with a good head
A stable, robust and solid team of developers, with a good head. That's what I found with Pentalog.
BewellConnect has been working with Pentalog since 2014 on several software telemedicine projects. Their professionalism, expertise, guidance, methodology, and timing have been wonderful. Pentalog is demonstrating competency in the required skillsets and good communications despite the remote working relationship. We want to express our gratitude to Pentalog for their productive collaboration with BewellConnect.
Pentalog helped MoovOne to build a complex application with good backend and frontend developers. It was a big technical challenge and the mission continued after the release to improve the product with our teams. The collaboration and the project were a success. We are very satisfied with this partnership.
Reach out to us,
describe your project
Choose a development category