Back to results
US 11,699,447 B2Granted
Systems and methods for determining traits based on voice analysis
AssigneeRovi Guides, Inc.
InventorsAnkur Anil Aher, Jeffry Copps Robert Jose
Life of this patent
Estimating the term…
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.
Claims20
A method comprising:
- receiving a voice query;
- determining, whether a voice of the voice query matches within a first confidence threshold a speaker identification (ID) among a plurality of speaker IDs stored in a speaker profile;
- in response to determining that the voice matches to the speaker ID within the first confidence threshold:
- bypassing a trait prediction engine;
- retrieving a trait among a plurality of traits stored in the speaker profile associated with the matched speaker ID;
- and
- providing a first content item based on the retrieved trait;
- and
- in response to determining that the voice does not match to any of the speaker IDs within the first confidence threshold:
- triggering the trait prediction engine to determine a second trait based on characteristics of the voice;
- and
- providing a second content item based on the second trait.
9 more elements
A system comprising:
- a memory configured to store a speaker profile,
- a control circuitry coupled to the memory and configured to:
- determine, whether a voice of a voice query matches within a first confidence threshold a speaker identification (ID) among a plurality of speaker IDs stored in the speaker profile;
- in response to determining that the voice matches to the speaker ID within the first confidence threshold:
- bypass a trait prediction engine;
- retrieve a trait among a plurality of traits stored in the speaker profile associated with the matched speaker ID;
- and
- provide a first content item based on the retrieved trait;
- and
- in response to determining that the voice does not match to any of the speaker IDs within the first confidence threshold:
- trigger the trait prediction engine to determine a second trait based on characteristics of the voice;
- and
- provide a second content item based on the second trait.
10 more elements
A system comprising:
- a memory configured to store a speaker profile,
- a control circuitry coupled to the memory and configured to:
- determine, whether a voice of a voice query matches within a first confidence threshold a speaker identification (ID) among a plurality of speaker IDs stored in the speaker profile;
- in response to determining that the voice matches to the speaker ID within the first confidence threshold:
- bypass a trait prediction engine;
- retrieve a trait among a plurality of traits stored in the speaker profile associated with the matched speaker ID;
- and
- provide a first content item based on the retrieved trait;
- determine that the voice query matched to the speaker ID within the first confidence threshold matches with a confidence score greater than the first confidence threshold;
- update the trait associated with the matched speaker ID with the confidence score greater than the first confidence threshold, wherein to update the retrieved trait the control circuitry is configured to:
- train the trait prediction engine to predict the updated trait based on biometric fingerprint generated from the voice query matched to the speaker ID with the confidence score greater than the first confidence threshold.
8 more elements
A method comprising:
- receiving a voice query;
- determining, whether a voice of the voice query matches within a first confidence threshold a speaker identification (ID) among a plurality of speaker IDs stored in a speaker profile;
- in response to determining that the voice matches the speaker ID within the first confidence threshold:
- bypassing a trait prediction engine;
- retrieving a trait among a plurality of traits stored in the speaker profile associated with the matched speaker ID;
- and
- providing a first content item based on the retrieved trait;
- in response to determining that the voice query matched to the speaker ID within the first confidence threshold matches with a confidence score that is greater than the first confidence threshold;
- updating the trait associated with the matched speaker ID with the confidence score greater than the first confidence threshold, wherein the updating comprises:
- training the trait prediction engine to predict the updated trait based on biometric fingerprint generated from the voice query matched to the speaker ID with the confidence score greater than the first confidence threshold.
7 more elements
Dependencies are inferred from the claim text.