Approaches to verifying the identity of speakers through objective, algorithmic characterizations of voice features and systems for implementing the same

US12334106B1 · kind B1 · utility

Assignee

• Verily Life Sciences LLC · US

Inventors

• Rui Wang · Shanghai, CN
• Andrew Campbell · Oslo, NO
• Danielle Schlosser · South San Francisco, US
• Dan Viet Duong · Los Altos Hills, US
• Bret E. Peterson · Lafayette, US
• Collin Walter · San Francisco, US
• Menachem Fromer · Newton, US
• Arthur Brant · Mountain View, US
• Honor Hsin · Palo Alto, US

Key dates

• Filing date: May 21, 2024
• Grant date: Jun 17, 2025
• Expiry date: May 21, 2044

Classification

• Technology area (CPC G): Physics
• CPC primary: G10L21/0208
• WIPO field: Medical technology
• WIPO sector: Instruments

Abstract

Introduced here are approaches to dynamically verifying the identity of an individual and assessing the health of the individual through objective, algorithmic characterizations of voice features derived from audio recordings created by the individual. These voice features may be paralinguistic features, non-linguistic features, or linguistic features. By characterizing these voice features, insights can be gleaned into how events represented in the audio recordings should be emotionally characterized. For example, for each audio recording created by the individual, a health management platform may calculate a valence measure that is based on the voice features established for that audio recording. These valence measures can be documented, for example, in a profile maintained for the individual, such that changes in health can be detected in a more reliable, quantitative manner.