US 12,739,463 B2Granted

Dynamic output of content based on detection of intended or unintended audio

AssigneeDISH Network Technologies India Private Limited

InventorsMansoor Ahmed, PrasannaKumar L, Visali Manoharan

Life of this patent

Estimating the term…

Loading patent…

Abstract

Systems and methods for a content receiver to dynamically determine if an audio signal includes intended audio or unintended audio based on a comparison between the audio signal and a plurality of intended-audio signatures or a plurality of unintended-audio signatures, or both. In response to determining that the audio signal includes unintended audio, the content receiver may output content based on an unintended-audio action. And in response to determining that the audio signal includes intended audio, the content receiver may: determine an intended-audio profile associated with the intended-signature that matches the audio signal; determines an intended-audio action based on the determined intended-audio profile; and outputs the content based on the intended-audio action.

Claims20

Dependent claims

A method, comprising:

receiving, by a content receiver, content for presentation to a user of the content receiver;
receiving, by the content receiver, an audio signal;
in response to receiving the audio signal, prompting, by the content receiver, a user to select a learning mode;
in response to the user selecting the learning mode:
employing, by the content receiver, a trained artificial intelligence mechanism to identify the audio signal as intended audio or unintended audio;
in response to identifying the audio signal as intended audio, generating, by the content receiver, an intended-audio signature for the audio signal generating an audio;
generating, by the content receiver, an intended-audio profile for the audio signal;
and
modifying, by the content receiver, a plurality of intended-audio profiles to included the generated intended-audio profile;
in response to the user failing to select the learning mode:
determining, by the content receiver, whether the audio signal includes intended audio or unintended audio based on a comparison between the audio signal and intended-audio signatures of the plurality of intended-audio profiles;
in response to determining that the audio signal includes unintended audio, outputting, by the content receiver, the content based on an unintended-audio action;
and
in response to determining that the audio signal includes intended audio:
determining, by the content receiver, an intended-audio profile from the plurality of intended-audio profiles that includes an intended-audio signature that matches the audio signal;
determining, by the content receiver, an intended-audio action based on the determined intended-audio profile;
and
outputting, by the content receiver, the content based on the intended-audio action.

15 more elements

A content receiver, comprising:

a memory configured to store computer instructions and to store a plurality of intended-audio signatures and corresponding intended-audio actions;
and
a processor system configured to execute the computer instructions to:
receive content for presentation to a user of the content receiver;
receive a first audio signal;
prompt a user to identify the first audio signal as intended audio or unintended audio;
in response to the audio signal being identified as intended audio:
generate an intended-audio signature for the first audio signal;
prompt a user to select an intended-audio action for the generated intended-audio signature;
and
store the generated intended-audio signature and corresponding user-selected intended-audio action in the memory;
receive a second audio signal;
compare the second audio signal to a plurality of intended-audio signatures;
determine whether the second audio signal includes intended audio or unintended audio based on the comparison, including:
determine that the second audio signal includes unintended audio in response to failing to identify a match between the second audio signal and the plurality of intended-audio signatures;
and
determine that the second audio signal includes intended audio in response to identifying a match between the second audio signal and an intended-audio signature;
in response to determining that the second audio signal includes unintended audio, output the content based on an unintended-audio action;
and
in response to determining that the second audio signal includes intended audio:
determine an intended-audio action that corresponds to the intended-audio signature that matches the second audio signal;
and
output the content based on the intended-audio action.

20 more elements

Dependencies are inferred from the claim text.

Facts

Application: 18/975,791Filed 10 Dec 2024
Published: US 2026/0164078 A111 Jun 2026
Granted: 15 Sep 2026
Term ends: Not estimatedThe source records don’t support an estimate.

Classification13 codes

H04N 21/42203
Input-only peripherals , i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS]: sound input…
H04N 21/4394
Processing of audio elementary streams: involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio…
H04N 21/233
Processing of content or additional data; Elementary server operations; Server middleware: processing of audio elementary streams
H04N 21/43615
Interfacing a local distribution network, e.g. communicating with another STB or one or more peripheral devices inside the home: interfacing a…