Adaptive volume control for media output devices and systems
AssigneeDISH Network L.L.C.
InventorPeter Gibbs
Life of this patent
Estimating the term…
Abstract
Various arrangements for performing dynamic volume control are provided. Audio characteristics of audio content being output to a user may be identified. Adjustments made to an audio volume setting by the user while the audio content is being output to the user can be monitored. A machine learning model can be trained based on the adjustments made to the audio volume setting by the user that are mapped with the audio characteristics of the audio content. After the machine learning model is trained, the audio volume setting can be adjusted based at least in part on the trained machine learning model analyzing audio content.
Claims20
A method for performing dynamic volume control, the method comprising:
- receiving, by a media output device, content comprising audio content;
- outputting, by the media output device to a user, the audio content;
- analyzing, by the media output device, audio characteristics of the content being output to the user;
- monitoring, by the media output device, adjustments made to an audio volume setting by the user while the audio content is being output to the user;
- mapping, by the media output device, the adjustments made to the audio volume setting by the user with the audio characteristics of the audio content, wherein mapping incorporates a defined delay between the adjustments and the audio characteristics of the audio content;
- training, by the media output device, a machine learning model based on the adjustments made to the audio volume setting by the user that are mapped with the audio characteristics of the audio content;
- after the machine learning model is trained, adjusting, by the media output device, the audio volume setting based at least in part on the trained machine learning model analyzing the audio content;
- and
- outputting, by the media output device, content using the adjusted audio volume setting.
A media output device, comprising:
- an interface through which media comprising audio content is received;
- an audio output component through which the audio content is output to a user;
- a processing system, comprising one or more processors, the processing system configured to:
- analyze audio characteristics of the audio content being output to the user;
- monitor adjustments made to an audio volume setting by the user while the audio content is being output to the user;
- map the adjustments made to the audio volume setting by the user with the audio characteristics of the audio content, wherein mapping the adjustments incorporates a defined delay between the adjustments and the audio characteristics of the audio content;
- train a machine learning model based on the adjustments made to the audio volume setting by the user that are mapped with the audio characteristics of the audio content;
- adjust the audio volume setting based at least in part on the trained machine learning model analyzing the audio content after the machine learning model is trained;
- and
- output the audio content using the adjusted audio volume setting via the audio output component.
A non-transitory processor-readable medium comprising processor-readable instructions configured to cause one or more processors to:
- receive content comprising audio content;
- cause the audio content to be output;
- analyze audio characteristics of the audio content being output;
- monitor adjustments made to an audio volume setting by a user while the audio content is being output to the user;
- map the adjustments made to the audio volume setting by the user with the audio characteristics of the audio content, wherein mapping incorporates a defined delay between the adjustments and the audio characteristics of the audio content;
- train a machine learning model based on the adjustments made to the audio volume setting by the user that are mapped with the audio characteristics of the audio content;
- adjust the audio volume setting based at least in part on the trained machine learning model analyzing the audio content after the machine learning model is trained;
- and
- cause the audio content to be output using the adjusted audio volume setting via an audio output component.
Dependencies are inferred from the claim text.