# US 2010/0169088 A1 · Automated demographic analysis

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2010/0169088 A1
- Document ID: US20100169088A1
- Status: Published application
- Kind: A1
- Application number: 12/344,981
- Filed: 2008-12-29
- Published: 2010-07-01
- Earliest claimed: 2008-12-29
- Assignees: AT&T Intellectual Property I, L.P.
- Inventors: Michael JOHNSTON; Hisao M. CHANG; Harry E. BLANCHARD; Bernard S. RENGER; Linda ROBERTS
- Web page: https://patentgrep.com/patent/US20100169088A1

## CPC

- G06Q 30/02: Marketing; Price estimation or determination; Fundraising
- G10L 17/00: Speaker identification or verification techniques
- G10L 25/78: Detection of presence or absence of voice signals (switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

A method of generating demographic information relating to an individual is provided. The method includes monitoring an environment for a voice activity of an individual and detecting the voice activity of the individual. The method further includes analyzing the detected voice activity of the individual and determining, based on the detected voice activity of the individual, a demographic descriptor of the individual.

## Claims

### Claim 1

A method of generating demographic information relating to an individual, comprising:
monitoring an environment for a voice activity of an individual;
detecting the voice activity of the individual;
analyzing the detected voice activity of the individual;
determining, based on the detected voice activity of the individual, a demographic descriptor of the individual.

### Claim 2 (depends on 1)

The method as set forth in claim 1, further comprising:
recognizing speech in the detected voice activity;
analyzing the recognized speech;
determining, based on the recognized speech, a content descriptor of the voice activity of the individual; and
correlating the demographic descriptor of the individual and the content descriptor of the voice activity of the individual to determine a response to be generated.

### Claim 3 (depends on 2)

The method as set forth in claim 2, further comprising:
correlating known information of the environment with the recognized and analyzed speech of the voice activity to determine, based on the correlated known information and the recognized and analyzed speech, the content descriptor of the voice activity of the individual.

### Claim 4 (depends on 1)

The method as set forth in claim 1, wherein a plurality of voice activities is detected, each belonging to one of a plurality of individuals, and the method further comprises selecting one of the plurality of voice activities to be a representative voice activity of the plurality of voice activities for analyzing the selected representative voice activity and determining, based on the selected representative voice activity, the demographic descriptor of the plurality of individuals.

### Claim 5 (depends on 4)

The method as set forth in claim 4, wherein the representative voice activity is selected by filtering the plurality of voice activities according to a predetermined paralinguistic property.

### Claim 6 (depends on 1)

The method as set forth in claim 1, wherein a plurality of the voice activities is detected, each belonging to one of a plurality of individuals, and wherein a demographic descriptor is determined for each of the plurality of individuals based on the detected voice activities of each of the plurality of individuals.

### Claim 7 (depends on 6)

The method as set forth in claim 6, further comprising:
generating a plurality of responses in the environment with each response being generated in response to one demographic descriptor of each of the plurality of individuals.

### Claim 8 (depends on 1)

The method as set forth in claim 1, further comprising:
generating a response in the environment in response to the determined demographic descriptor.

### Claim 9 (depends on 8)

The method as set forth in claim 8, further comprising:
correlating the demographic descriptor with known information of the individual to determine the response to be generated.

### Claim 10 (depends on 8)

The method as set forth in claim 8, further comprising:
looking up the demographic descriptor in a database to determine the response to be generated.

### Claim 11 (depends on 1)

The method as set forth in claim 1, further comprising:
detecting visual activity of the individual;
analyzing the detected visual activity of the individual; and
correlating the analyzed voice activity and the analyzed visual activity of the individual to determine the demographic descriptor.

### Claim 12 (depends on 1)

The method as set forth in claim 1, wherein the voice activity is detected with an audio capture device that includes an input configured to enable the individual to input an inputted activity for determining the demographic descriptor.

### Claim 13 (depends on 1)

The method as set forth in claim 1, further comprising:
storing the determined demographic descriptor in a database and associating it with the individual for creating a profile of the individual.

### Claim 14 (depends on 13)

The method as set forth in claim 13, wherein the profile associated with the individual is configured to be accessible by the individual for displaying the profile on a social networking website.

### Claim 15 (depends on 1)

The method as set forth in claim 1, further comprising:
detecting the voice activity of the individual for a predetermined period of time to analyze the voice activity detected over the predetermined period of time to determine a general demographic descriptor of the individual.

### Claim 16 (depends on 1)

The method as set forth in claim 1, wherein the voice activity is detected with an audio capture device, and
wherein the detected voice activity is transmitted over a network for analyzing the voice activity to determine the demographic descriptor.

### Claim 17

A system for generating demographic information relating to an individual, comprising:
an audio capture device disposed in an environment for detecting a voice activity of an individual; and
an analyzer that analyzes the detected voice activity to determine, based on the detected voice activity, a demographic descriptor of the individual.

### Claim 18 (depends on 17)

The system as set forth in claim 17, wherein the audio capture device is configured to detect a plurality of the voice activities, each belonging to one of a plurality of individuals, and to select one of the plurality of voice activities to be a representative voice activity of the plurality of voice activities for determining, based on the selected representative voice activity, the demographic descriptor of the plurality of individuals.

### Claim 19

A tangible computer readable medium for storing a computer program for generating demographic information relating to an individual, the computer readable medium comprising:
an executable monitoring code segment that monitors an environment for a voice activity of an individual;
an executable detecting code segment that detects the voice activity of the individual in the environment;
an executable analyzing code segment that analyzes the detected voice activity; and
an executable determining code segment that determines, based on the detected voice activity of the individual, a demographic descriptor of the individual.

### Claim 20 (depends on 19)

The computer readable medium as set forth in claim 19, wherein the detecting code segment detects a plurality of the voice activities, each belonging to one of a plurality of individuals, and the computer readable medium further comprises:
an executable selecting code segment that selects one of the plurality of voice activities to be a representative voice activity,
wherein the determining code segment determines, based on the selected representative voice activity, the demographic descriptor of the plurality of individuals.
