Making machines listen

Our technology listens “between” the lines of text and gives you what speech recognition, for example, cannot give you. Based on decades of scientific research in the fields of psychology, linguistics and voice research, electrical engineering, and computer science, we offer customized products that analyse the acoustics of speech and music signals. Our technology detects when and how something is said, not what.

We can help you deliver voice emotion recognition in order to better understand your customer’s feelings. And we can go beyond that: what about estimating a speaker’s age, gender, or personality simply from the voice? Our technology can provide all of that – fully automated, of course.

Real-life acoustic environments

audEERING’s technology is not limited to “clean” laboratory environments but can deal with real-life acoustic conditions. It can locate voice signals even in highly noisy scenarios and uses intelligent speech enhancement technology to improve the clarity of speech.

Paralinguistic speech analysis

Automated paralinguistic speech analysis is a young field with a great potential for improving efficiency of several business fields, such as call centre quality control, targeted advertising, or emotion-sensitive virtual agents. Our products allow you to detect a multitude of attributes from the human voice, such as emotion and affective states, age, depression, alertness, or personality. Further, our technology is able to analyse vocal parameters which could indicate vocal pathological disorders or psychological disorders like depression.

Intelligent music analysis

We love music, and so does our audio analysis software. It can tag music by mood, extract chorus segments, identify key and chords, detect tempo, meter, dance-style, and genre. Furthermore, it robustly tracks beats in a song and can detect singing voice segments within music recordings.

Sound analysis

You need to analyse something that is neither speech nor music? For example, classify acoustic sceneries, detect breaking glass or unusual sounds in a high security environment? You need someone to develop your own, customized, speech, music, or sound analysis software?

Don’t hesitate to contact us! We are glad to help you and adapt our technology to solve your problem. We have experts in machine learning and audio signal processing, which can help you solve your task quickly and efficiently.

Any questions? Don’t hesitate to contact us!