PeakProfiling

Pioneers in advanced sound analytics

Areas of expertise

Pediatrician examining a little girl

Medical Voice Analytics

Mental and physical diseases and other medical conditions can be detected purely from the sound of the human voice.

Example: We have strong clinical evidence for the detection of ADHD via voice analytics.

Machinery in factory

Industrial Sound Emission Analysis

Most technical applications or processes emit some kind of sound - which we analyze for predictive maintenance or spotting specific failures. Example: defective electric motors can be identified from the sound during end-of-line testing.

People talking

Affective Voice Computing

Also mental conditions like emotions or well-being can be measured from the sound of the human voice. Example: voice-steered devices can derive information about how the user is doing.

Langner Hasler Portrait

Mission

"Imagine you detect a disease years before it becomes severe by a simple phone call...or you spot a defect in a machine before a crash happens. The impact we will have with our approach is truly fascinating."
Claudio Hasler & Dr. Jörg Langner
PeakProfiling Founders

Technological Focus

AdobeStock 408300183

Combining quantitative musicology with AI

We combine voice and sound analytics knowledge from musicology with AI. ​​PeakProfiling originated as a spin-off from the faculties of Mathematics and Musicology of Humboldt University in Berlin. Over several decades of research we've created a complete system of sound - especially speech sound - analysis. This knowledge is combined with state-of-the art approaches in artificial intelligence - a unique mixture with a wide variety of applications.

Company History: From Mozart to Analytics

002
The technical origins of ​​PeakProfiling go back to the 90ties, when Co-founder and CTO of PeakProfiing, Dr. Langner, conducted his PhD and Postdoc research in quantitative musicology. He was heavily fascinated by music and how to understand it algorithmically: for example, he wanted to understand mathematically why Mozart touches so many people with his compositions. Based on these roots, and three decades later, PeakProfiling is a cutting-edge provider of sound analytics technology.

Recent News

ADHD paper scaled

Attention-Deficit / Hyperactivity Disorder (ADHD) is a frequent disorder not only among children, but also in adults. Especially for the latter, diagnostics is a challenge and objective biomarkers are lacking. In a clinical study in collaboration with Chartié Berlin and Forschungszentrum Jülich, PeakProfiling successfully predicted ADHD from the voice. With more than 1000 recordings from almost 700 participants, this is one of the biggest purely clinical studies ever conducted in the field. The success rates of the algorithms are comparable to single rating doctors.

Explaining Terminology in Voice Technology

“Paralinguistics”, “Voice Biomarkers”, “Speech-to-Text” or “Voice Biometrics”, just to mention a few - terminology in Voice Tech can be confusing and we are frequently asked for clarification by our clients. We therefore put together some explanations of the basic concepts.  

Situations in which we can typically help you

Voice

You have lots of voice data but you are unsure if / how you can process them in a compliant way with optimal technology.

You want to measure the emotiol state of a speaker from their voice and need a cutting-edge technology partner.

You tried to build a voice biomarker on your own, but success rates (accuary, sensitivities, specificities, AUCs, etc.) were too low.

Machine

You want to predict a critical type of defect in your machine, but conventional approaches at predictive maintenance are unsuccessful.

You want a specific lifetime prediction or real-time information on the remaining lifetime of your machine/ component, not a general estimate by the manufacturer or subjective human judgement.

You feel like Industry 4.0 is a buzzword and you want to see a hands-on solution.

Shopping Basket