Company Profile
Key Facts
- Founded in 2012 in Gilching near Munich, Germany
- Development of SaaS and SDKs for AI based audio analysis
- Over 60 employees
- 55 % of our employees hold an academic degree, 31 % a PhD
- 2 offices in Gliching near Munich and Berlin
- Holder of a Proof-of-Concept Grant by the European Research Council funded under H2020
- Multi-award-winning technology, including the Bavarian Innovation Prize 2018, and the VDE Award 2019
About
audEERING was founded in 2012 as a spin-off of the Technical University of Munich. Today, audEERING is the only European company driving innovation in the field of intelligent audio analysis and vocal expression AI. Using innovative machine intelligence and deep learning techniques, audEERING’s products can automatically analyze e. g. acoustic scenes, speaker states as well as mood states. audEERING’s customers include multinational companies such as Huawei, BMW, GfK, Red Bull Media House and Ipsos.
Technology
audEERING’s technology percepts human voice and interpretes it on a deep level. The technology evaluates voice recordings based on acoustic parameters regarding e.g. pitch, voice characteristics and prosodic elements. Based on this evaluation it enables to refer to the person’s mood and health status. The evaluation combines the linguistic analysis of a person’s answers with up to 7,000 acoustic components. This works based on Deep Learning processes, using an algorithm which gathers data sets to classify, sort and match them. audEERING’s technology can identify arousal and valence in order to assign them to an expression. Voice analysis in health enables for early detection, as well as enhanced therapy and monitoring of many diseases.
Our Products
- Health AI: AI SoundLab is audEERING‘s study platform for your research on voice, health and AI applications. Our AI detects even slight symptoms, significantly increasing the chances for early detection. With COVID-19 or Parkinson’s we reach up to 92% accuracy.
- Audio AI for Software & Hardware: devAIce® offers easy integration of AI based audio analysis into our client’s products. It enables expression and scene detection to enhance apps, software or smart devices.
- Market Research: Expressions of clients are analyzed through voice and sound events like laughter. This allows our customer to speed up their product testing and gain deeper insights with different target groups.
- Call Center: Agents get real time information about the mood of the caller. They can react quicker and more emphatic to increase customer satisfaction significantly.
- Gaming Industry: Our vocal expression AI technology is utilized in three main use cases. Active expression detection as input for games, passive monitoring of expressions for child safety, and play testing applications for faster development iterations.