AUTOMATED QUERY DETECTION IN INTERACTIVE CONTENT
Systems and methods may be used to automatically detect a query in interactive content. A system may implement a method that includes receiving an audible signal. The method may include determining that a portion of the audible signal includes speech. The method may include translating at least the portion of the audible signal. The portion of the audible signal may be translated into a natural language output. The method may include generating an identifier (ID) associated with the speech. The ID maybe generated on a condition that the natural language output includes a trigger. The method may include generating an inaudible signal that includes the ID. The method may include synchronizing the inaudible signal with the audible signal. The method may include transmitting the audible signal a ta first frequency. The method may include transmitting the inaudible signal at a second frequency.
1 - 20 . (canceled)
21 . A method, comprising:
receiving an audible signal from a media device, wherein the audible signal comprises a natural language output;
in response to determining that the natural language output comprises a trigger phrase, querying a database for a next content identification (ID) based on the audible signal;
determining an electronic device associated with the next content ID;
determining a wake command associated with the electronic device; and
outputting the wake command and the next content ID.
22 . The method of claim 21 , wherein the electronic device comprises a voice-activated device connected to a content system via a network.
23 . The method of claim 21 , wherein generating the wake command and the next content ID comprises:
generating an inaudible phrase; and
generating a text-to-speech signal that includes the inaudible phrase.
24 . The method of claim 23 , further comprising:
converting the text-to-speech signal to a speech-formatted response.
25 . The method of claim 21 , further comprising:
in response to determining that the trigger phrase is not included within the database, storing the trigger phrase within the database.
26 . The method of claim 25 , wherein a frequency, a device type, and a device status associated with the electronic device is stored within the database.
27 . The method of claim 21 , wherein determining that the natural language output comprises a trigger phrase is performed by at least one of: an automated speech recognition (ASR) engine, or a natural language understanding (NLU) engine.
28 . A system comprising:
control circuitry configured to:
receive an audible signal from a media device, wherein the audible signal comprises a natural language output;
in response to determining that the natural language output comprises a trigger phrase, query a database for a next content identification (ID) based on the audible signal;
determine an electronic device associated with the next content ID;
determine a wake command associated with the electronic device; and
output the wake command and the next content ID.
29 . The system of claim 28 , wherein the electronic device comprises a voice-activated device connected to a content system via a network.
30 . The system of claim 28 , wherein generating the wake command and the next content ID comprises:
generating an inaudible phrase; and
generating a text-to-speech signal that includes the inaudible phrase.
31 . The system of claim 30 , further comprising:
converting the text-to-speech signal to a speech-formatted response.
32 . The system of claim 28 , further comprising:
in response to determining that the trigger phrase is not included within the database, storing the trigger phrase within the database.
33 . The system of claim 32 , wherein a frequency, a device type, and a device status associated with the electronic device is stored within the database.
34 . The system of claim 28 , wherein determining that the natural language output comprises a trigger phrase is performed by at least one of: an automated speech recognition (ASR) engine, or a natural language understanding (NLU) engine.
35 . A non-transitory computer-readable medium having instructions encoded thereon that, when executed by control circuitry, cause the control circuitry to:
receive an audible signal from a media device, wherein the audible signal comprises a natural language output;
in response to determining that the natural language output comprises a trigger phrase, query a database for a next content identification (ID) based on the audible signal;
determine an electronic device associated with the next content ID;
determine a wake command associated with the electronic device; and
output the wake command and the next content ID.
36 . The non-transitory computer-readable medium of claim 35 , wherein the electronic device comprises a voice-activated device connected to a content system via a network.
37 . The non-transitory computer-readable medium of claim 35 , wherein generating the wake command and the next content ID comprises:
generating an inaudible phrase; and
generating a text-to-speech signal that includes the inaudible phrase.
38 . The non-transitory computer-readable medium of claim 37 , further comprising:
converting the text-to-speech signal to a speech-formatted response.
39 . The non-transitory computer-readable medium of claim 35 , further comprising:
in response to determining that the trigger phrase is not included within the database, storing the trigger phrase within the database.
40 . The non-transitory computer-readable medium of claim 39 , wherein a frequency, a device type, and a device status associated with the electronic device is stored within the database.
41 . The non-transitory computer-readable medium of claim 35 , wherein determining that the natural language output comprises a trigger phrase is performed by at least one of: an automated speech recognition (ASR) engine, or a natural language understanding (NLU) engine.