# US 12,112,758 B2 · Systems and methods for determining traits based on voice analysis

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

- Number: US 12,112,758 B2
- Document ID: US12112758B2
- Status: Granted
- Kind: B2
- Application number: 18/203,214
- Filed: 2023-05-30
- Published: 2023-09-28
- Granted: 2024-10-08
- Earliest claimed: 2020-06-22
- Assignees: Rovi Guides, Inc.
- Applicants: Rovi Guides, Inc.
- Inventors: Ankur Anil Aher; Jeffry Copps Robert Jose
- Web page: https://patentgrep.com/patent/US12112758B2

## CPC

- G10L 17/06: Decision making techniques; Pattern matching strategies
- G10L 17/04: Training, enrolment or model building
- G10L 17/18: Artificial neural networks; Connectionist approaches
- G10L 17/26: Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Systems and methods are provided herein for determining one or more traits of a speaker based on voice analysis to present content item to the speaker. In one example, the method receives a voice query and determines whether the voice query matches within a first confidence threshold of a speaker identification (ID) among a plurality of speaker IDs stored in a speaker profile. In response to determining that the voice query matches to the speaker ID within the first confidence threshold, the method bypasses a trait prediction engine and retrieves a trait among the plurality of traits in the speaker profile associated with the matched speaker ID. The method further provides a content item based on the retrieved trait.

## Claims

### Claim 1

A method comprising:
receiving a voice query;
generating a biometric fingerprint of the voice query;
comparing the generated biometric fingerprint with a plurality of biometric fingerprints stored within a profile of a user;
determining whether a match exists between the generated biometric fingerprint and one of the plurality of biometric fingerprints stored within the profile of the user, wherein the match is associated with a confidence score;
in response to determining that the confidence score associated with the match is above a first confidence threshold, retrieving a trait stored in the profile of the user that is associated with the matched biometric fingerprint of the plurality of biometric fingerprints; and
in response to determining that the confidence score associated with the match is below the first confidence threshold and above a second confidence threshold:
determining a trait corresponding to the generated biometric fingerprint; and
updating the plurality of biometric fingerprints stored within the profile of the user with the determined trait corresponding to the generated biometric fingerprint.

### Claim 2 (depends on 1)

The method of claim 1, wherein the biometric fingerprint represents at least one of a tone, a pitch or a pace of a voice of the user.

### Claim 3 (depends on 1)

The method of claim 1, wherein the profile of the user is a database.

### Claim 4 (depends on 3)

The method of claim 3, wherein each of the plurality of biometric fingerprints stored within the database is associated with a unique speaker identification (ID) respectively.

### Claim 5 (depends on 1)

The method of claim 1, wherein determining whether the match exists comprises:
comparing the traits associated with the generated biometric fingerprint with the traits associated with each of the plurality of biometric fingerprints stored within the profile of the user respectively; and
generating the confidence score based on a correlation between the compared traits.

### Claim 6 (depends on 1)

The method of claim 1, wherein the first confidence threshold is pre-determined based on speech features previously captured from the voice query.

### Claim 7 (depends on 1)

The method of claim 1, wherein retrieving the trait stored in the profile of the user comprises:
using a trait determination application to access a database containing the plurality of biometric fingerprints.

### Claim 8 (depends on 1)

The method of claim 1, wherein the trait may be one of an age range, a gender or an ethnicity.

### Claim 9 (depends on 1)

The method of claim 1, wherein updating the plurality of biometric fingerprints comprises:
replacing the matched biometric fingerprint stored in the profile of the user with the biometric fingerprint generated from the voice query.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
in response to determining that the confidence score associated with the match is below the second confidence threshold:
triggering a trait determination application to determine a second trait based on the generated biometric fingerprint of the voice query; and
updating the plurality of biometric fingerprints stored within the profile of the user with the second trait.

### Claim 11

A system comprising:
a memory; and
control circuitry configured to:
receive a voice query;
generate a biometric fingerprint of the voice query;
compare the generated biometric fingerprint with a plurality of biometric fingerprints stored within a profile of a user in the memory;
determine whether a match exists between the generated biometric fingerprint and one of the plurality of biometric fingerprints stored within the profile of the user, wherein the match is associated with a confidence score;
in response to determining that the confidence score associated with the match is above a first confidence threshold, retrieve a trait stored in the profile of the user that is associated with the matched biometric fingerprint of the plurality of biometric fingerprints; and
in response to determining that the confidence score associated with the match is below the first confidence threshold and above a second confidence threshold:
determine a trait corresponding to the generated biometric fingerprint; and
update the plurality of biometric fingerprints stored within the profile of the user with the determined trait corresponding to the generated biometric fingerprint.

### Claim 12 (depends on 11)

The system of claim 11, wherein the biometric fingerprint represents at least one of a tone, a pitch or a pace of a voice of the user.

### Claim 13 (depends on 11)

The system of claim 11, wherein the profile of the user is a database.

### Claim 14 (depends on 13)

The system of claim 13, wherein each of the plurality of biometric fingerprints stored within the database is associated with a unique speaker identification (ID) respectively.

### Claim 15 (depends on 11)

The system of claim 11, wherein control circuitry is further configured to:
compare the traits associated with the generated biometric fingerprint with the traits associated with each of the plurality of biometric fingerprints stored within the profile of the user respectively; and
generate the confidence score based on a correlation between the compared traits.

### Claim 16 (depends on 11)

The system of claim 11, wherein the first confidence threshold is pre-determined based on speech features previously captured from the voice query.

### Claim 17 (depends on 11)

The system of claim 11, wherein control circuitry is further configured to:
use a trait determination application to access a database containing the plurality of biometric fingerprints.

### Claim 18 (depends on 11)

The system of claim 11, wherein the trait may be one of an age range, a gender or an ethnicity.

### Claim 19 (depends on 11)

The system of claim 11, wherein control circuitry is further configured to:
replace the matched biometric fingerprint stored in the profile of the user with the biometric fingerprint generated from the voice query.

### Claim 20 (depends on 11)

The system of claim 11, wherein control circuitry is further configured to:
in response to determining that the confidence score associated with the match is below the second confidence threshold:
trigger a trait determination application to determine a second trait based on the generated biometric fingerprint of the voice query; and
update the plurality of biometric fingerprints stored within the profile of the user with the second trait.