# US 12,010,392 B2 · Adaptive volume control for media output devices and systems > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,010,392 B2 - Document ID: US12010392B2 - Status: Granted - Kind: B2 - Application number: 17/583,589 - Filed: 2022-01-25 - Published: 2023-07-27 - Granted: 2024-06-11 - Earliest claimed: 2022-01-25 - Assignees: DISH Network L.L.C. - Applicants: DISH Network L.L.C. - Inventors: Peter Gibbs - Web page: https://patentgrep.com/patent/US12010392B2 ## CPC - H04N 21/4852: {for modifying audio parameters, e.g. switching between mono and stereo} - H04N 21/4394: {involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams (arrangements characterised by components specially adapted for monitoring, identification or recognition of audio in broadcast systems H04H60/58)} - H04N 21/44008: {involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream (arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59)} - H04N 21/44213: {Monitoring of end-user related data (arrangements for monitoring the users' behaviour or opinions in broadcast systems H04H60/33)} - H04N 21/4666: {using neural networks, e.g. processing the feedback provided by the user} - H04R 3/04: for correcting frequency response - H04R 2430/01: Aspects of volume control, not necessarily automatic, in sound systems - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - H04R: LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS (producing sounds with frequency not determined by supply frequency G10K) ## 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. ## Claims ### Claim 1 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. ### Claim 2 (depends on 1) The method for performing dynamic volume control of claim 1, wherein the machine learning model classifies the audio content into an audio class of a plurality of audio classes and adjusts the audio volume setting based on the audio class into which the audio content is classified. ### Claim 3 (depends on 2) The method for performing dynamic volume control of claim 2, wherein the machine learning model is a neural network. ### Claim 4 (depends on 1) The method for performing dynamic volume control of claim 1, further comprising: outputting, by the media output device to the user, video content, wherein the content comprises the video content; analyzing, by the media output device, video characteristics of the video content being output to the user; and training, by the media output device, the machine learning model based on the video characteristics. ### Claim 5 (depends on 1) The method for performing dynamic volume control of claim 1, where the audio volume setting is adjusted relatively based on a previous audio volume setting. ### Claim 6 (depends on 1) The method for performing dynamic volume control of claim 1, wherein the media output device is a television receiver comprising a plurality of tuners that are configured to receive broadcast television channels. ### Claim 7 (depends on 1) The method for performing dynamic volume control of claim 1, wherein outputting the audio content using the adjusted audio volume setting comprises outputting the audio content via one or more audio speakers. ### Claim 8 (depends on 1) The method for performing dynamic volume control of claim 1, wherein outputting the audio content using the adjusted audio volume setting comprises outputting the audio content to a separate audio output device for output. ### Claim 9 (depends on 1) The method for performing dynamic volume control of claim 1, wherein analyzing audio characteristics of the audio content comprises: creating an acoustic fingerprint for a chunk of the audio content, whereby a plurality of acoustic fingerprints are created for a plurality of chunks of the audio content. ### Claim 10 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. ### Claim 11 (depends on 10) The media output device of claim 10, wherein the machine learning model classifies the audio content into an audio class of a plurality of audio classes and adjusts the audio volume setting based on the audio class into which the audio content is classified. ### Claim 12 (depends on 11) The media output device of claim 11, wherein the machine learning model is a neural network. ### Claim 13 (depends on 10) The media output device of claim 10, further comprising a user interface, wherein the processing system is configured to adjust the audio volume setting relatively based on a previous manual audio volume setting received from the user via the user interface. ### Claim 14 (depends on 10) The media output device of claim 10, further comprising a plurality of tuners configured to receive broadcast television via a television service provider network, wherein the media output device is a television receiver. ### Claim 15 (depends on 10) The media output device of claim 10, wherein the audio output component is a speaker. ### Claim 16 (depends on 10) The media output device of claim 10, wherein the audio output component is an audio output interface that outputs the audio content to a speaker separate from the media output device. ### Claim 17 (depends on 10) The media output device of claim 10, wherein the processing system being configured to analyze the audio characteristics of the audio content comprises the processing system being configured to: analyze a chunk of the audio content to create a plurality of sets of audio data, whereby a plurality of sets of audio data are created. ### Claim 18 (depends on 10) The media output device of claim 10, wherein the media output device further comprises an electronic display on which video content of the media output. ### Claim 19 (depends on 10) The media output device of claim 10, further comprising a non-transitory processor readable medium that stores a volume model datastore, wherein the volume model datastore stores a plurality of trained machine learning models from which the machine learning model is selected to dynamically control the audio volume setting. ### Claim 20 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.