Audio processing techniques for semantic audio recognition and report generation

Patent metadata

Field	Value
Publication number	US-11837208-B2
Application number	US-202117403626-A
Country	US
Kind code	B2
Filing date	Aug 16, 2021
Priority date	Dec 21, 2012
Publication date	Dec 5, 2023
Grant date	Dec 5, 2023

Abstract

Example methods, apparatus and articles of manufacture to determine semantic information for audio are disclosed. Example apparatus disclosed herein are to process an audio signal obtained by a media device to determine values of a plurality of features that are characteristic of the audio signal, compare the values of the plurality of features to a first template having corresponding first ranges of the plurality of features to determine a first score, the first template associated with first semantic information, compare the values of the plurality of features to a second template having corresponding second ranges of the plurality of features to determine a second score, the second template associated with second semantic information, and associate the audio signal with at least one of the first semantic information or the second semantic information based on the first score and the second score.

First claim

What is claimed is:

1. An computing system comprising:
at least one processor;
at least one memory including computer readable instructions that, upon execution by the at least one processor, cause the computing system to at least:
process a first frame of an audio signal to determine first values of a plurality of features of the audio signal;
associate the first frame of the audio signal with at least one of first semantic information or second semantic information based on comparison of the first values of the plurality of features to a first template associated with the first semantic information and comparison of the first values of the plurality of features to a second template associated with the second semantic information, the first template having corresponding first ranges of the plurality of features, the second template having corresponding second ranges of the plurality of features;
process a second frame of the audio signal to determine second values of the plurality of features; and
associate the second frame of the audio signal with at least one of the first semantic information or the second semantic information based on comparison of the second values of the plurality of features to the first template associated with the first semantic information and comparison of the second values of the plurality of features to the second template associated with the second semantic information.

2. The computing system of claim 1 , wherein the computer readable instructions further cause, upon execution by the at least one processor, the computing system to:
compare the first values of the plurality of features to the first template associated with the first semantic information to determine a first score;
compare the first values of the plurality of features to the second template associated with the second semantic information to determine a second score; and
associate the first frame of the audio signal with at least one of the first semantic information or the second semantic information based on the first score and the second score.

3. The computing system of claim 1 , wherein the computer readable instructions further cause, upon execution by the at least one processor, the computing system to:
compare the first values of the plurality of features to the first template associated with the first semantic information to determine a first plurality of scores corresponding to the plurality of features;
compare the first values of the plurality of features to the second template associated with the second semantic information to determine a second plurality of scores corresponding to the plurality of features; and
associate the first frame of the audio signal with at least one of the first semantic information or the second semantic information based on the first plurality of scores and the second plurality of scores.

4. The computing system of claim 3 , wherein the computer readable instructions further cause, upon execution by the at least one processor, the computing system to:
determine a first histogram based on the first plurality of scores; and
determine a second histogram based on the second plurality of scores.

5. The computing system of claim 1 , wherein the plurality of features includes at least one of an audio timbre feature, a beat feature, a loudness feature, or a spectral histogram feature.

6. The computing system of claim 5 , wherein the first ranges include at least one of a first range for the audio timbre feature, a first range for the beat feature, a first range for the loudness feature, or a first range for a spectral histogram feature, and the second ranges include at least one of a second range for the audio timbre feature, a second range for the beat feature, a second range for the loudness feature, or a second range for the spectral histogram feature.

7. The computing system of claim 5 , wherein respective ones of the first ranges are associated with corresponding first weights, and respective ones of the second ranges are associated with corresponding second weights.

8. At least one article of manufacture comprising non-transitory computer readable instructions which, when executed, cause at least one processor to at least:
process a first frame of an audio signal to determine first values of a plurality of features of the audio signal;
associate the first frame of the audio signal with at least one of first descriptive information or second descriptive information based on comparison of the first values of the plurality of features to a first template associated with the first descriptive information and comparison of the first values of the plurality of features to a second template associated with the second descriptive information, the first template having corresponding first ranges of the plurality of features, the second template having corresponding second ranges of the plurality of features;
process a second frame of the audio signal to determine second values of the plurality of features; and
associate the second frame of the audio signal with at least one of the first descriptive information or the second descriptive information based on comparison of the second values of the plurality of features to the first template associated with the first descriptive information and comparison of the second values of the plurality of features to the second template associated with the second descriptive information.

9. The at least one article of manufacture of claim 8 , wherein the instructions further cause, when executed, the at least one processor to:
compare the first values of the plurality of features to the first template associated with the first descriptive information to determine a first score;
compare the first values of the plurality of features to the second template associated with the second descriptive information to determine a second score; and
associate the first frame of the audio signal with at least one of the first descriptive information or the second descriptive information based on the first score and the second score.

10. The at least one article of manufacture of claim 8 , wherein the instructions further cause, when executed, the at least one processor to:
compare the first values of the plurality of features to the first template associated with the first descriptive information to determine a first plurality of scores corresponding to the plurality of features;
compare the first values of the plurality of features to the second template associated with the second descriptive information to determine a second plurality of scores corresponding to the plurality of features; and
associate the first frame of the audio signal with at least one of the first descriptive information or the second descriptive information based on the first plurality of scores and the second plurality of scores.

11. The at least one article of manufacture of claim 10 , wherein the instructions further cause, when executed, the at least one processor to:
determine a first histogram based on the first plurality of scores; and
determine a second histogram based on the second plurality of scores.

12. The at least one article of manufacture of claim 8 , wherein the plurality of features includes at least one of an audio timbre feature, a beat feature, a loudness feature, or a spectral histogram feature.

13. The at least one article of manufacture of claim 12 , wherein the first ranges include at least one of a first range for the audio timbre feature, a first range for the beat feature, a first range for the loudness feature, or a first range for a spectral histogram feature, and the second range

Assignees

• Nielsen Co Us Llc

Inventors

• Neuhauser Alan
• Stavropoulos John

Classifications

• G10H1/40 Primary

  Rhythm · CPC title

• G06F40/40

  Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) · CPC title

• G10L15/1815 Primary

  Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning · CPC title

• G10L19/018

  Audio watermarking, i.e. embedding inaudible data in the audio signal · CPC title

• G10H2210/036

  of musical genre, i.e. analysing the style of musical pieces, usually for selection, filtering or classification · CPC title