Dynamically adjust audio attributes based on individual speaking characteristics

Patent metadata

Field	Value
Publication number	US-10154346-B2
Application number	US-201715494342-A
Country	US
Kind code	B2
Filing date	Apr 21, 2017
Priority date	Apr 21, 2017
Publication date	Dec 11, 2018
Grant date	Dec 11, 2018

Abstract

Embodiments are directed towards analyzing content to adjust audio attributes of an audio component of the content to improve a user's audible perception of the content. The content is analyzed to determine an accent of an individual speaking in the content, an ethnic origin or gender of the individual, a genre of the content, or user preferences of the user, or some combination thereof. One or more of these determined characteristics is utilized to select and adjust at least one audio attribute of the audio component of the content, e.g., the volume, base, or treble. The audio component of the content is then output to at least one audio output device based on the at least one adjusted audio attribute. These audio attribute adjustments can improve a user's perception of the audio component, which can improve the user's understanding of the individual speaking in the content.

First claim

The invention claimed is:

1. A method that is executed on a content receiver, comprising:
receiving content for presentation to a user, the content includes an audio component;
analyzing the audio component of the content to determine a language accent of an individual speaking in the content;
determining an ethnic origin of the individual speaking based on visual characteristics of the individual speaking;
adjusting at least one audio attribute of the audio component of the content based on the language accent and the determined ethnic origin of the individual speaking in the content; and
outputting the audio component of the content to at least one audio output device based on the at least one adjusted audio attribute.

2. The method of claim 1 , wherein adjusting the at least one audio attribute includes at least one of:
adjusting an overall volume of the audio component;
adjusting a bass control of the audio component; and
adjusting a treble control of the audio component.

3. The method of claim 1 , wherein adjusting the at least one audio attribute includes:
separating the audio component of the content into a plurality of audio channels to be output to a plurality of audio output devices; and
performing at least one of:
modifying a volume of a first audio channel of the plurality of audio channels;
modifying a bass control of a second audio channel of the plurality of audio channels; and
modifying a treble control of a third audio channel of the plurality of audio channels.

4. The method of claim 1 , further comprising:
determining a genre of the content based on metadata received with the content; and
adjusting the at least one audio attribute based on the determined genre.

5. The method of claim 1 , further comprising:
determining at least one listening preference of the user; and
performing further adjustments to the at least one audio attribute based on the at least one listening preference of the user.

6. The method of claim 1 , further comprising:
determining a location of each of the at least one audio output device;
determining a location of the user relative to the location of the at least one audio output device; and
adjusting the at least one audio attribute for each of the at least one audio output device based on the user's determined location.

7. The method of claim 1 , further comprising:
receiving at least one manual adjustment to the at least one audio attribute; and
providing the at least one manual adjustment to a content-distribution server for determining at least one preferred audio attribute for a region in which the content receiver is located.

8. The method of claim 1 , further comprising:
determining a geographical region where the content receiver is located; and
receiving a plurality of default audio attributes for the content receiver based on a plurality of preferred audio attributes identified for the geographical region.

9. The method of claim 8 , wherein the plurality of preferred audio attributes are identified for the geographical region based on manual adjustments of audio attributes by other users in the geographical region.

10. The method of claim 1 , wherein analyzing the audio component of the content to determine the language accent of the individual speaking includes:
determining the language accent of the individual speaking based on a combination of a plurality of speech characteristics that includes at least one of pronunciation, grammar, word choice, slurring of words, use of made-up words, or phonemes.

11. A system, comprising:
a content receiver that includes a first memory for storing first instructions and a first processor that executes the first instructions to perform actions, the actions, including:
receiving content for presentation to a user, the content including an audio component;
analyzing the audio component of the content to determine a gender of an individual speaking in the content;
analyzing the audio component of the content to determine an accent of the individual speaking;
analyzing the audio component of the content to determine an ethnic origin of the individual speaking;
determining a location of the user relative to a location of each of a plurality of audio output devices;
adjusting at least one audio attribute of the audio component of the content based on the gender of the individual speaking in the content, the accent of the individual speaking in the content, the determined ethnic origin of the individual speaking in the content, and the user's location;
utilizing the at least one adjusted audio attribute to output the audio component of the content to the plurality of audio output devices;
receiving at least one manual adjustment to the at least one audio attribute; and
providing the at least one manual adjustment to a content-distribution server for determining at least one preferred audio attribute for a region in which the user is located; and

the content-distribution server includes a second memory for storing second instructions and a second processor that executes the second instructions to perform other actions, the other actions, including:
determining a geographical region where the content receiver is being utilized by the user;
receiving manual adjustments of audio attributes by other users in the geographical region;
identifying a plurality of preferred audio attributes for the geographical region based on the manual adjustments of audio attributes by the other users; and
providing, independent of the content, a plurality of default audio attributes for the content receiver based on a plurality of preferred audio attributes identified for the geographical region.

12. The system of claim 11 , wherein adjusting the at least one audio attribute includes at least one of:
adjusting a volume of the audio component;
adjusting a bass control of the audio component; and
adjusting a treble control of the audio component.

13. The system of claim 11 , wherein adjusting the at least one audio attribute includes:
separating the audio component of the content into a plurality of audio channels to be output to a plurality of audio output devices; and
performing at least one of:
modifying a volume of a first audio channel of the plurality of audio channels;
modifying a bass control of a second audio channel of the plurality of audio channels; and
modifying a treble control of a third audio channel of the plurality of audio channels.

14. The system of claim 11 , further comprising:
determining a genre of the content based on metadata received with the content; and
adjusting the at least one audio attribute based on the determined genre.

15. A content receiver, comprising:
an input that receives program content;
a memory that stores at least instructions; and
a processor that executes the instructions to:
analyze an audio component of the program content to determine at least one speaking characteristic of an individual speaking in the content;
determine dialect of the individual speaking based on the at least one speaking characteristic;
determine at least one audio attribute of the audio component to adjust based on the dialect;
adjust the at least one audio attribute of the audio component based on the dialect of the individual speaking in the content; and
output the audio component of the content to at least one audio output device based on the at least one adjusted audio attribute.

16. The content receiver of claim 15 , wherein the processor executes further instructions to adjust the at least one audio attribute by

Assignees

• Dish Tech Llc

Inventors

• Raghavan Srinath
• Ghimire Saksham

Classifications

• G10L21/003

  Changing voice quality, e.g. pitch or formants · CPC title

• H04S7/303

  Tracking of listener position or orientation · CPC title

• G10L15/005

  Language recognition · CPC title

• G10L25/51

  for comparison or discrimination · CPC title

• H04R5/04 Primary

  Circuit arrangements, {e.g. for selective connection of amplifier inputs/outputs to loudspeakers, for loudspeaker detection, or for adaptation of settings to personal preferences or hearing impairments (combinations of amplifiers H03F3/68; stereophonic systems H04S)} · CPC title