Canary SpeechThe AI-powered voice biomarker technology company has been awarded a patent for developing a paired neural network for voice analysis, aiming to advance the field of voice biomarker technology.
of Patents We describe a paired neural network system for improving AI-powered voice analysis, which allows for accurate monitoring of subtle changes in an individual’s voice by comparing it to past samples.
This approach could enable the creation of highly personalized voice biomarkers, which could improve the accuracy of detecting various health conditions by focusing on changes rather than individual voice characteristics.
Canary technology processes over 15 million data elements per minute of conversational audio by computing feature vectors from audio samples and analyzing them with neural networks.
The technology enables audio biomarker assessment for a range of diseases and human conditions, providing the ability to objectively measure in real time and compare specific measurements across different points in time.
The system uses transformer neural networks and regression techniques to assess health status and changes based on voice patterns.
“This will significantly improve clinical team members’ ability to track and understand patient progress over time,” Canary CEO Henry O’Connell said. Get MobiHealthNews by email.
For example, when a patient is discharged from hospital after a significant health problem, a member of the clinical team often follows up by phone every two weeks to assess the patient’s progress, identify any potential problems, and take appropriate measures to ensure a stable recovery.
“Caregivers may ask patients a number of questions, including about stress, anxiety, fatigue and quality of sleep,” O’Connell said. “Patients will be evaluated for potential complications such as pulmonary artery tortuosity, fatigue and pain.”
He said Canary Speech measures many of these health conditions during the call and can compare how a patient is doing since the last call.
“All of this is available in real time to provide clinical team members with actionable information to help them guide conversations, explore concerns based on objective data, and use their judgement to take informed action to ensure the best outcomes for patients,” he said.
Larger trends
Canary is actively expanding its impact in the areas of healthcare and veterans support: Last month, the company announced a partnership with the Veteran Business Project, a nonprofit focused on helping veteran entrepreneurs.
This collaboration will utilize Canary’s technology Give veterans the tools to monitor their mental health, access advice on staying well, and identify factors that may contribute to stress, allowing them to stay focused on business goals while managing their health.
Canary Speech in June The $13 million Series A funding was led by Cortes Capital (Love’s Private Equity) and included 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 to Power machine learning speech models for healthcare applications.
The company has integrated its technology with remote patient monitoring and virtual care provider Life365 to create a unified platform.
Canaries too Partnering with Hackensack Meridian HealthThe collaboration included a strategic investment from the nonprofit health care network and its Bear’s Den Innovation Accelerator program.
Other notable companies in healthcare voice recognition technology include: Voiceitt and NVIDIA.
