Patent · US Active

Identification of people using multiple types of input

US8510110B2 · kind B2 · utility

5Cited by

23References

18Claims

0Family size

Assignee

Microsoft Corporation · US

Inventors

Cha Zhang · Sammamish, US
Paul Viola · Seattle, US
Pei Yin · Atlanta, US
Ross Cutler · Duvall, US
Xinding Sun · Lompoc, US
Yong Rui · Sammamish, US

Key dates

Filing date	Jul 11, 2012
Grant date	Aug 13, 2013
Priority date	—
Expiry date	Jul 11, 2032

Classification

Technology area (CPC G)Physics
CPC primaryG10L2021/02166
WIPO fieldAudio-visual technology
WIPO sectorElectrical engineering

Abstract

Systems and methods for detecting people or speakers in an automated fashion are disclosed. A pool of features including more than one type of input (like audio input and video input) may be identified and used with a learning algorithm to generate a classifier that identifies people or speakers. The resulting classifier may be evaluated to detect people or speakers.

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