Canary SpeechSIHA, Inc., an AI-based voice biomarker technology company, has been awarded a patent for the development of a paired neural network for voice analysis, with the aim of advancing the field of voice biomarker technology.
that patent Includes a paired neural network system to improve AI-based voice analysis. It can accurately monitor subtle changes in an individual’s voice compared to previous samples.
This approach enables the creation of highly personalized voice biomarkers that can improve the accuracy of detecting a variety of health conditions by focusing on voice changes rather than individual voice characteristics.
Canary technology processes over 15 million data points per minute of conversational speech by computing feature vectors of speech samples and analyzing them with neural networks.
This technology enables assessment of vocal biomarkers for a variety of diseases and human conditions, objectively measuring them in real time and comparing specific measurements across different times.
The system uses transformer neural networks and regression techniques to assess health status and identify changes based on voice patterns.
“This will significantly improve the ability of clinical team members to track and understand a patient’s progress longitudinally,” said Canary CEO Henry O’Connell. Check out MobiHealthNews via email.
For example, when a patient is discharged from the hospital after experiencing a serious health issue, a member of the clinical team will follow up with the patient by phone, typically every two weeks, to assess progress, identify potential problems, and take appropriate action to ensure a stable recovery.
“Caregivers can ask patients a lot of questions about stress, anxiety, fatigue, sleep quality, etc.,” O’Connell said. “Patients are assessed for potential complications, such as pulmonary edema, fatigue, pain, etc.”
He said Canary Speech can measure several health conditions during a phone call and compare the patient’s condition since the last phone call.
“All of this is delivered in real time to provide actionable information to clinical team members to guide conversations, explore areas of concern based on objective data, and use judgment to take informed action to ensure the best outcomes for patients,” he said.
The bigger trend
Canary has been actively expanding its reach across healthcare and veteran support. Last month, the company announced a partnership with the Veteran Business Project, a nonprofit that supports veteran entrepreneurs.
This collaboration leverages Canary’s technology. We provide Veterans with tools to monitor their mental health, access wellness recommendations, and identify potential stressors, so they can focus on their business goals while managing their wellness.
In June, Canary Speech was secured. It raised $13 million in Series A funding led by Cortes Capital (Love’s Private Equity) and contributed by SMK (Japan), Hackensack Meridian Health, and Sorenson Communications.
The company said the funding will support its continued innovation and growth.
Last year, Canary expanded its capabilities through a partnership with Microsoft, leveraging the software giant’s AI technology. Improving machine learning speech models for healthcare applications.
The company has integrated its technology with Life365, a remote patient monitoring and virtual care provider, to create a unified platform.
Canary too Joining forces with Hackensack Meridian Health.Collaboration that includes strategic investments from nonprofit health networks and the Bear’s Den innovation accelerator program.
Other notable players in the medical voice recognition technology space include: Voiceitt and NVIDIA.
