US 9,437,193 B2 · Environment adjusted speaker identification

Abstract

Computerized estimation of an identity of a user of a computing system. The system estimates environment-specific alterations of a received user sound that is received at the computing system. The system estimates whether the received user sounds is from a particular user by use of a corresponding user-dependent audio model. The user-dependent audio model may be stored in a multi-system store accessible such that the method may be performed for a given user across multiple systems and on a system that the user has never before trained to recognize the user. This reduces or even eliminates the need for a user to train a system to recognize the voice of a user, and allows multiple systems to take advantage of previous training performed by the user.

Claims20

Dependent claims

A method for estimating an identity of a user of a computing system, the method comprising:

an act of estimating environment-specific alterations of a received user sound that is received at the computing system;
an act of facilitating a formulation of an expected audio model of a user's sound when a corresponding user-dependent audio model is subject to the estimated environment-specific alterations;
an act of obtaining a comparison result of comparing the received user sound with the formulation of the expected audio model;
and
an act of estimating whether the user corresponding to the user-dependent audio model is the same as the user that emitted the user sound based on the comparison result,
the user-dependent audio model being stored in a multi-system store.

3 more elements

Dependencies are inferred from the claim text.

Environment adjusted speaker identification

Life of this patent

Environment adjusted speaker identification

Life of this patent

Abstract

Claims20