Canary Speech Receives Patent for Paired Neural Networks Technology

Canary Speech, a voice biomarker technology company, has been granted a U.S. patent for its paired neural networks system, officially titled Paired Neural Networks for Speech Analysis.

The patent US20230072242A1, details a sophisticated system employing paired neural networks to analyze and interpret speech. This technology uses advanced artificial intelligence to process vocal inputs, providing insights into a speaker's health, emotional state, and other critical metrics.

"We are thrilled to receive this patent, which represents years of hard work and innovation by our talented team," said Henry O'Connell, CEO of Canary Speech, in a statement. "This technology has the potential to change how we understand and interact with speech, opening up new possibilities across various industries."

Paired neural network technology identifies subtle shifts in an individual's voice by analyzing it against previous samples from the same person. This breakthrough enables the delivery of highly personalized vocal biomarkers, enhancing accuracy by filtering out individual vocal traits and focusing on changes that may indicate the presence of various diseases and other health conditions.

Canary Speech uses vocal biomarkers that capture a data set of more than 15 million data elements every minute of conversational speech.

"The paired neural networks system is a game-changer in speech analysis. Where available, using previous voice samples from a patient creates the ability to focus on an individual's specific speech patterns and vocal tract in truly personalized medicine. We are eager to see the impact it will have in healthcare, customer service, and beyond," said Nate Blaylock, chief technology officer of Canary Speech, in a statement.