Vocal Biomarker Technology
People communicate with their voices. From the past until now, the culture of voice has transformed its shape and form to become an integral part of our lives, and it communicates an enormous variety of information from person to person to support our daily living. When you greet someone close to you, you may be able to tell how they are by the tone of their voice, for example, “They sound like they are fine today,” or “They sound like they are not doing well today.”
People communicate a lot of information about their well-being through their voices.
Sometimes they sound like they are doing well.
But other times, their voice tells us that they are not doing so well.
PST has developed vocal biomarker technology that checks for changes in one’s body and mind through voice, separate from the vocabulary and messages being spoken.
The technology does this by analyzing the characteristics of a voice before it even produces words, detecting problems with cognitive function and mind condition, as well as physical issues.
We are helping to create a healthy society where people can identify their medical and healthcare issues through voice data from various aspects of their daily lives.
Our vocal biomarker technology enables any person who speaks any language in any country around the world to “visualize changes in physical and mental conditions” regardless of the meaning, content, or vocabulary of the language, because it analyzes the characteristics of the “voice” before it becomes spoken words. It is a unique technology originating in Japan and bound for the world, and it can contribute to people’s health in a broad range of areas, from the medical domain, where precision is required for medical devices, to the healthcare domain, where it can be used to check conditions in daily life thanks to its high versatility. We believe that this technology that “unlocks the secret of voice” will directly lead to a healthy future for all humankind.
Here we introduce the basic mechanism of our “voice analysis technology,” which is expected to be applied to various domains, mainly in the two domains of “medical (diagnosis, changes in pathological conditions*2)” and “healthcare (health management, conditions).”
*: Pathological conditions: Disease-specific voice symptoms