Speech is a complex process that requires coordination with our brain, muscles, and respiratory system.
Diagnosing Disease by Voice – using digital Bio-Markers to tell If You Have a Chronic Disease
Biomarkers are patterns in your voice like pitch, tone, volume, rhythm and rate that can reveal a variety of health conditions.
Many companies have started research to develop Biomarkers for early diagnosing.
Research on – Automated assessment of psychiatric disorders using speech
There are many barriers to accessing mental health assessments including cost and stigma. Even when individuals receive professional care, assessments are intermittent and may be limited partly due to the episodic nature of psychiatric symptoms. Therefore, machine‐learning technology using speech samples obtained in the clinic or remotely could one day be a biomarker to improve diagnosis and treatment. To date, reviews have only focused on using acoustic features from speech to detect depression and schizophrenia.
Winterlight Labs, Inc. in Collaboration with Johnson & Johnson Innovation plans to Develop a Digital Biomarker for Diagnosis of Early Stage Alzheimer’s Disease.
Winterlight Labs has developed technology that extracts 500 features from speech and language and uses artificial intelligence (AI) to create disease-specific digital biomarkers. Winterlight’s current digital biomarker for AD is 91% accurate in distinguishing Alzheimer’s from healthy aging using two minutes of speech.
Team of experts at Winterlight leverage computational linguistics, cognitive neuroscience, and machine learning and have developed a proprietary, tablet-based technology that assesses cognitive health (including memory, thinking, and reasoning) by analysing hundreds of language markers from short snippets of speech.
Research has increasingly focused on developing treatments for AD in its earliest phases, when pathological changes have started to occur in the brain, but cognitive decline is not yet evident. It is this period of time at which therapeutic intervention has the greatest chance of providing a meaningful benefit to the patient. To date, this pre-symptomatic period cannot be detected with traditional tests of cognitive function, and a key future goal is to identify AD patients prior to the emergence of symptoms, to allow treatment to be initiated when patients are still cognitively healthy.
A biomarker for clinical research
Paper-based cognitive assessments are slow, subjective and often coarse. Winterlight has developed a speech-based cognitive assessment that analyzes short snippets of speech and uses AI to objectively measure cognition via hundreds of vocal biomarkers in speech and language. Winterlight can support clinical trials and studies for a wide range of central nervous system disorders.
Beyond Verbal is using Voice and AI to extract human emotions and reveal Vocal Biomarkers – acoustic features indicating various health conditions.
Vocalis Health is a leading pioneer of voice-enabled AI technology using proprietary vocal biomarkers for personalized healthcare screening & triage. It has also now developed COVID-19 screening tool.
VocalisCheck* – COVID-19 Vocal Biomarker
VocalisCheck is a software solution that assesses the voice of a person whose COVID-19 status is unknown, without additional information or prior knowledge about the individual user.
- Quick voice check which can be seamlessly integrated into workflows
- Software-only product with cloud-based algorithm database
How does it work?
A single voice sample is recorded using a mobile app or web-based tool, and a cloud-based AI analytics engine provides feedback within a minute or two.
User counts from
50 to 70
Recording transformed to
picture and compared to