IP Library › Granted Patent US 12681938
Granted Patent B2
US 12681938 · App. 18/086,865 · Granted Jul 14, 2026

Methods and apparatus for determining a mood profile associated with media data

Inventors: Ching-Wei Chen (Oakland, CA); Kyogu Lee (Albany, CA); Peter C. DiMaria (Berkeley, CA); Markus K. Cremer (Orinda, CA)
Assignee: Gracenote, Inc.
G06F16/24578G06F16/4387G10H1/0008G10H2240/085G10H2240/131
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12681938
App. No.
18/086,865
Granted
Jul 14, 2026
Kind
B2
Abstract

An example method involves comparing a primary element of a first piece of audio data to a primary element of a second piece of audio data; based on the comparing of the primary elements, determining that the first and second pieces of audio data have the same predominant mood category; in response to determining that the first and second pieces of audio data have the same predominant mood category, comparing a first mood score of the primary element of the first piece of audio data to a second mood score of the primary element of a second piece of audio data; determining that an output of the comparison of the two mood scores exceeds a threshold value; and in response to determining that the output of the comparison of the two mood scores exceeds the threshold value, providing an indicator to an application.

Claims (40)

1 . A computer-implemented method for matching of audio data comprising:

comparing, by one or more processors, a primary element of a first piece of audio data to a primary element of a second piece of audio data, wherein the primary element of the first piece of audio data identifies a predominant mood category of the first piece of audio data, wherein the primary element of the second piece of audio data identifies a predominant mood category of the second piece of audio data, and wherein a trained classifier generates mood-category scores and the primary elements used for the comparison are obtained by partial retrieval of the mood-category scores, wherein the partial retrieval reduces at least one of a required memory or a required processing power for the comparison;

determining, by the one or more processors, that the first and second pieces of audio data have the same predominant mood category based on comparing the primary elements of the first and second pieces of audio data to a correlates matrix;

in response to determining that the first and second pieces of audio data have the same predominant mood category, comparing, by the one or more processors, a first mood score of the primary element of the first piece of audio data to a second mood score of the primary element of a second piece of audio data;

determining, by the one or more processors, that an output of the comparison of the first mood score and the second mood score exceeds a threshold value; and

in response to determining that the output of the comparison of the first mood score and the second mood score exceeds the threshold value, providing an indicator to an application, by the one or more processors, that causes the application to perform an operation associated with the second piece of audio data.

2 . The computer-implemented method of claim 1 , wherein providing the indicator to the application comprises displaying a selectable indication of the second piece of audio data on a user interface.

3 . The computer-implemented method of claim 1 , wherein providing the indicator to the application comprises accessing the second piece of audio data from data storage.

4 . The computer-implemented method of claim 1 , wherein providing the indicator to the application comprises playing the second piece of audio data using a signal generation device.

5 . The computer-implemented method of claim 1 , wherein the threshold value is set automatically by the application.

6 . The computer-implemented method of claim 1 , wherein the threshold value is a user-preferred threshold set by a user of the application.

7 . The computer-implemented method of claim 1 , wherein providing the indicator to the application comprises adding the second piece of audio data to a playlist.

8 . The computer-implemented method of claim 1 , further comprising extracting, by the one or more processors, low-level audio feature data from an audio signal associated with the audio data to determine the primary element of the first piece of audio data.

9 . The computer-implemented method of claim 1 , wherein the partial retrieval reduces both the required memory and the processing power for the comparison.

10 . A non-transitory tangible machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations for matching of audio data comprising:

comparing a primary element of a first piece of audio data to a primary element of a second piece of audio data, wherein the primary element of the first piece of audio data identifies a predominant mood category of the first piece of audio data, wherein the primary element of the second piece of audio data identifies a predominant mood category of the second piece of audio data, and wherein a trained classifier generates mood-category scores, and wherein the primary elements used for the comparison are obtained by partial retrieval of the mood-category scores, wherein the partial retrieval reduces at least one of a required memory or a required processing power for the comparison;

determining that the first and second pieces of audio data have the same predominant mood category based on comparing the primary elements of the first and second pieces of audio data to a correlates matrix;

in response to determining that the first and second pieces of audio data have the same predominant mood category, comparing a first mood score of the primary element of the first piece of audio data to a second mood score of the primary element of a second piece of audio data;

determining that an output of the comparison of the first mood score and the second mood score exceeds a threshold value; and

in response to determining that the output of the comparison of the first mood score and the second mood score exceeds the threshold value, providing an indicator to an application that causes the application to perform an operation associated with the second piece of audio data.

11 . The non-transitory tangible machine-readable storage medium of claim 10 , wherein providing the indicator to the application comprises displaying a selectable indication of the second piece of audio data on a user interface.

12 . The non-transitory tangible machine-readable storage medium of claim 10 , wherein providing the indicator to the application comprises accessing the second piece of audio data from data storage.

13 . The non-transitory tangible machine-readable storage medium of claim 10 , wherein providing the indicator to the application comprises playing the second piece of audio data using a signal generation device.

14 . The non-transitory tangible machine-readable storage medium of claim 10 , wherein the threshold value is set automatically by the application.

15 . The non-transitory tangible machine-readable storage medium of claim 10 , wherein the threshold value is a user-preferred threshold set by a user of the application.

16 . The non-transitory tangible machine-readable storage medium of claim 10 , wherein providing the indicator to the application comprises adding the second piece of audio data to a playlist.

17 . A computing system comprising:

a memory that stores instructions;

a database;

one or more processors configured by the instructions to perform operations for matching of audio data comprising:

comparing, by the one or more processors, a primary element of a first piece of audio data to a primary element of a second piece of audio data, wherein the primary element of the first piece of audio data identifies a predominant mood category of the first piece of audio data, wherein the primary element of the second piece of audio data identifies a predominant mood category of the second piece of audio data, and wherein a trained classifier generates mood-category scores and the primary elements used for the comparing are obtained by partial retrieval of the mood-category scores, wherein the partial retrieval reduces at least one of a required memory or a required processing power for the comparison;

determining, by the one or more processors, that the first and second pieces of audio data have the same predominant mood category based on comparing the primary elements of the first and second pieces of audio data to a correlates matrix;

in response to determining that the first and second pieces of audio data have the same predominant mood category, comparing, by the one or more processors, a first mood score of the primary element of the first piece of audio data to a second mood score of the primary element of a second piece of audio data;

determining, by the one or more processors, that an output of the comparison of the first mood score and the second mood score exceeds a threshold value; and

in response to determining that the output of the comparison of the first mood score and the second mood score exceeds the threshold value, providing an indicator to an application, by the one or more processors, that causes the application to perform an operation associated with the second piece of audio data.

18 . The computing system of claim 17 , wherein providing, by the one or more processors, the indicator to the application comprises displaying a selectable indication of the second piece of audio data on a user interface.

19 . The computing system of claim 17 , wherein providing, by the one or more processors, the indicator to the application comprises accessing the second piece of audio data from data storage.

20 . The computing system of claim 17 , wherein providing, by the one or more processors, the indicator to the application comprises playing the second piece of audio data using a signal generation device.

21 . The computing system of claim 17 , wherein the threshold value is set automatically by the application.

22 . The computing system of claim 17 , wherein the threshold value is a user-preferred threshold set by a user of the application.