Photo: Alexander Spatari/Getty Images
Canary Speech is expanding its vocal biomarker technology into the consumer health market through a partnership with JubileeTV, embedding AI-driven speech analysis directly into video calls between older adults and their families.
The integration marks the first time Canary Speech's technology has been deployed outside clinical and research environments.
The platform analyzes acoustic and linguistic features from short segments of natural conversation, generating nondiagnostic indicators related to cognitive function, mood, stress, energy and overall wellness.
These insights are produced passively during JubileeTV video calls, allowing families to track changes over time without requiring additional devices or active testing.
Canary Speech converts 40 seconds of natural conversation into high-density, machine-readable acoustic data.
"Rather than analyzing what someone says, we analyze how they say it, capturing thousands of acoustic features every few milliseconds, including pitch dynamics, timing, prosody, jitter, shimmer, pauses and vocal energy patterns," Henry O’Connell, CEO of Canary Speech, told MobiHealthNews.
These features are processed through machine learning models trained on clinically labeled datasets associated with cognitive and behavioral health conditions, such as Mild Cognitive Impairment, Alzheimer's disease, anxiety, depression and stress-related states.
Within seconds, the system produces normalized decision-support scores for domains like cognition, mood and fatigue.
O'Connell explained that because the analysis runs on standard digital audio, Canary operates on ordinary devices like smartphones, tablets, desktops, call center systems or ambient documentation tools – no scripted tasks, special hardware or supervised protocols are required.
"The technology integrates directly into existing workflows, enabling passive insight without additional burden on clinicians or patients," he said. "Because voice is natural and noninvasive, monitoring feels like a conversation, not testing."
O'Connell said this improves engagement and reduces stigma around mental and cognitive health screening, and for caregivers, it provides objective trend visibility.
"For health systems and payers, it enables low-cost risk stratification across aging populations and earlier intervention, reducing downstream costs of unmanaged dementia, depression and frailty," O'Connell said.
THE LARGER TREND
Noninvasive biomarker technologies, like voice, allow care teams to detect change between visits, in the environments where people live. Instead of relying solely on annual screenings or symptom-triggered appointments, clinicians can monitor cognitive and behavioral health trends passively and proactively.
"Ambient AI transforms everyday interaction into structured, privacy-preserving health intelligence," O'Connell said. "This signals a transition from reactive care to proactive care extending clinical-grade visibility into the home without adding friction to patients, caregivers or providers."
In 2024, Canary Speech received a patent for its neural network-powered speech analysis, and raised $13 million to develop its speech recognition software.
The company had earlier partnered with Microsoft to leverage the software giant's AI technology to expand its machine learning speech models and accelerate AI-enabled speech analysis technology.
