devAIce® integrates audio analysis in software and hardware. It is the core technology of audEERING. In its audio analysis it combines a variety of features such as emotion detection, speaker attributes, scene detection, voice, and music activity. It allows customers to use audEERING’s AI technology in their business application in a simple way to create a developer friendly experience with a great user usability.
With the Prodct Owner Talk series audEERING introduces the human intelligence behind this technology. Following some questions, you will learn more about the product and the developer itself.
The human intelligence behind the Voice AI | Meet the devAIce product owner Milenko Saponja
The Product Owner Talk series starts with Milenko Saponja, who is one of the software developers of audEERING with more than six years of experience in different research and development departments in the company. With his specializing in robotics, he was also able to be a key participant in the #ERIK project, which aimed to develop an innovative therapy concept for autistic children. For this, the #robotpepper was adapted with audEERING’s core AI-technology devAIce®.
As one of Milenko’s main tasks as a product owner responsible for devAIce®, is the scope of product development:
How is the product going to look like in six months within one year? What features should be included? Which functionality should be added with what kind of priority?
Therefore, the devAIce team is in close contact with other departments to know their working schedule and current needs. Of high importance is customer communication, to know exactly what the customer would and could need. Constant improvement in a product life cycle is important for the further development, within a license product such as devAIce®.
Development process of an AI technology
How does a process of an AI technology look like? For the Product owner Milenko and his devAIce team the development process spins around the integration of all different models which the internal research team is working on and transform it to a product that the customers can use. Therefore, a solid team in which every team member should know the most about the product and contributes its own expertise, the basic of the processes.
Product opportunities and potential applications
The license product, co-developed by Milenko, provides the customers the possibility to easily use our audEERING technology, in simple terms “to analyze any audio file of the human voice for instance emotion recognition, gender detection, age, speaking intonation, speaking rate and so on. Just based on acoustic it can tell you where you are. For example, if you are in the office or are in a car. Certain events like a crying of a baby, telephone ringing, music is playing in the background is also possible.”
Find more regards customers, projects and success stories.
Examples for possible use cases
Integrating devAIce in call centers is a fascinating opportunity to detect the tone of voice. It is about to find out how satisfied customers are or how friendly the agents themselves are. Find more about the call center use case in Jabra’s Engage AI platform, which is powered by audEERING.
Also, in the field of market research around the general opinion and satisfaction of customers towards a particular product devAIce and in general Voice AI technology creates a huge innovation.
Further, the application goes in IoT devices and in any basic human-machine interaction, such as interaction with robots and cars. Just to name a few.
devAIce® – a cutting-edge technology?
“devAIce provides users the usage of the latest AI technology in a simple way so, you literally need a single line of code to get acoustic emotion recognition and what is also important to mention here you don’t need some GPU servers to write, but it can also run on your physical device.”
Personal learning about working with Audio AI
In the end we asked Milenko what he has learned about speaking and voices since working on devAIce® for audEERING? “I learned how much we humans still don’t know about the voice, which is the most important. We use it just for daily communication, but it can be used for much more than that. For instance, when you have a cold which is easily noticeable in your voice, but this measurable information can be used for so much more. Also not easy noticeable states like depression detection, stress level detection, Alzheimer and Parkinson. I’m sure that at the moment the possibility of voice are not explored enough but on the other side I’m sure that in the future they will be much more explored and become much more relevant”.
Get to know our core technology devAIce® and get a Factsheet
Have you seen our other technical blog posts with detailed developer information about devAIce® Web API 4.1.0 and devAIce® SDK 3.7.0?
Q&A
- If devAIce® can be used without internet connection?
Basically with our SDK solution the customer can run the license on his physical device and therefore there is no need because it doesn’t consume that much high computational power. If necessary to need an Internet connection it is predominantly for the license query itself.
- Do I have to pay for these updates?
Customers with subscription plans or licenses eligible for free updates do not have to pay for this update. - Do I have to update?
No, you may continue to use whatever version you are currently on. devAIce SDK users need to explicitly opt-in to receive the new version. Nevertheless, we recommend to update to the latest version when possible in order to benefit from the latest model additions, improvements and fixes. - Where can i get more information?
If you are interested in updating to the new version of devAIce or have any questions on these updates or devAIce in general, please contact audEERING’s Customer Experience Manager Sylvia Szylar (sszylar@audeering.com).