Patent · US Active

Systems and methods for identifying diminished capacity of a voice call participant based on audio data analysis

US12039531B2 · kind B2 · utility

0Cited by
1References
26Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 26, 2023
Grant dateJul 16, 2024
Priority date
Expiry dateApr 26, 2043

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH04M3/2236
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Systems and methods are described herein for identifying diminished capacity of a voice call participant based on audio data analysis. A server generates an audio image based on an audio file comprising speech data corresponding to a first user on a voice call. The server determines a diminished capacity score based on one or more characteristics of the audio image analyzed using a deep learning classification model. The server applies a security protocol to an account associated with the first user when the diminished capacity score is at or above a threshold value. The server receives a transaction request corresponding to the account from the first user. The server processes the transaction request based on the security protocol applied to the account.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.