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 may be 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 at a first frequency. The method may include transmitting the inaudible signal at a second frequency.
1. A method comprising:
receiving an audible signal at a user content consumption device;
determining that a portion of the audible signal includes speech;
translating at least the portion of the audible signal into a natural language output;
generating, at the user content consumption device, on a condition that the natural language output includes a trigger, an identifier (ID) associated with the speech;
determining a device type;
selecting a frequency for an inaudible signal based on the determined device type;
generating the inaudible signal at the selected frequency, wherein the inaudible signal includes the ID;
synchronizing the inaudible signal with the audible signal; and
transmitting the audible signal at a first frequency and the inaudible signal at the selected frequency.
2. The method of claim 1 , wherein the transmitting further comprises:
transmitting the audible signal at the first frequency and the inaudible signal at the selected frequency simultaneously to a voice-activated electronic device.
3. The method of claim 1 , wherein the trigger is based on a speech inflection.
4. The method of claim 1 , wherein generating the inaudible signal comprises:
generating an inaudible phrase; and
generating a text-to-speech signal that includes the inaudible phrase.
5. The method of claim 4 , wherein generating the inaudible phrase comprises:
receiving the natural language output;
querying a database for a next ID; and
outputting a response that includes the next ID.
6. The method of claim 5 further comprising:
associating the natural language output to the next ID; and
storing the associated natural language output and the next ID in the database.
7. The method of claim 1 , wherein generating the inaudible signal comprises:
transmitting a request associated with the ID;
determining a wake command based on the device type;
determining a trigger phrase based on the ID; and
outputting the inaudible signal including the wake command and the trigger phrase.
8. The method of claim 7 further comprising:
determining a device status; and
outputting the inaudible signal at the selected frequency based on the device status.
9. The method of claim 7 further comprising:
determining an instruction; and
outputting the inaudible signal including the wake command, the instruction, and the trigger phrase.
10. A user content consumption device comprising:
a receiver configured to receive an audible signal at the user content consumption device;
a transmitter; and
a processor comprising:
an automated speech recognition (ASR) engine configured to determine that a portion of the audible signal includes speech; and
a natural language understanding (NLU) engine configured to translate at least the portion of the audible signal into a natural language output;
the processor further configured to:
generate, at the user content consumption device, an identifier (ID) associated with the speech on a condition that the natural language output includes a trigger;
determine a device type;
select a frequency for an inaudible signal based on the determined device type;
generate the inaudible signal at the selected frequency, wherein the inaudible signal includes the ID; and
synchronize the inaudible signal with the audible signal; and
the transmitter configured to transmit the audible signal at a first frequency and the inaudible signal at the selected frequency.
11. The user content consumption device of claim 10 , wherein the transmitter is configured to transmit the audible signal at the first frequency and the inaudible signal at the selected frequency simultaneously to a voice-activated electronic device.
12. The user content consumption device of claim 10 , wherein the trigger is based on a speech inflection.
13. The user content consumption device of claim 10 , wherein the processor is further configured to:
generate an inaudible phrase; and
generate a text-to-speech signal that includes the inaudible phrase.
14. The user content consumption device of claim 10 , wherein the processor is further configured to:
receive the natural language output;
query a database for a next ID; and
output a response that includes the next ID.
15. The user content consumption device of claim 14 , wherein the processor is further configured to:
associate the natural language output to the next ID; and
store the associated natural language output and the next ID in the database.
16. The user content consumption device of claim 10 , wherein the processor is further configured to:
transmit a request associated with the ID;
determine a wake command based on the device type;
determine a trigger phrase based on the ID; and
output the inaudible signal including the wake command and the trigger phrase.
17. The user content consumption device of claim 16 , wherein the processor is further configured to:
determine a device status; and
output the inaudible signal at the selected frequency based on the device status.
18. The user content consumption device of claim 16 , wherein the processor is further configured to:
determine an instruction; and
output the inaudible signal including the wake command, the instruction, and the trigger phrase.