Intent driven voice interface
An audio stream received from an audio transceiver. The audio stream is in an environment that includes audio of a first user. An acoustic communication of the first user is detected from the audio stream. An audio intent trigger of the first user is identified from the audio stream and based on the acoustic communication. An assistance action for the first user is initiated in response to the audio intent trigger and by a voice-based interface.
1. A method comprising:
receiving, from an audio transceiver of a computing device of a second user, an audio stream in an environment that includes audio of a first user, wherein the audio transceiver is integrally coupled to the computing device of the second user, and wherein the computing device of the second user is located in the environment;
detecting, from the audio stream, an acoustic communication of the first user;
identifying, from the audio stream and based on the acoustic communication, an audio intent trigger of the first user; and
initiating, in response to the audio intent trigger and by a voice-based interface, an assistance action for the first user, wherein the assistance action includes instructing a computing device of the first user to generate an audiovisual alert.
2. The method of claim 1 , wherein the audio intent trigger is identified by a central server, and wherein the method further comprises:
transmitting the audio stream to the central server.
3. The method of claim 2 , wherein the detecting of the acoustic communication is by the computing device of the second user in the environment, and wherein the transmitting is responsive to the detecting.
4. The method of claim 1 , wherein the identifying includes performing a machine learning technique on the audio stream.
5. The method of claim 4 , wherein the machine learning technique is based on a predefined general profile.
6. The method of claim 5 , wherein the identifying is performed by the computing device of the second user that is located in the environment.
7. The method of claim 5 , wherein the machine learning technique is based on a predefined first user profile, wherein the identifying is performed by a secure element of the computing device of the second user, and wherein the method further comprises:
encrypting the predefined first user profile; and
transmitting the encrypted predefined first user profile to the secure element of the computing device of the second user.
8. The method of claim 4 , wherein the machine learning technique is based on a predefined first user profile.
9. The method of claim 8 , wherein the predefined first user profile includes a trigger word.
10. The method of claim 9 , wherein the predefined first user profile includes a repeat factor for a number of times the first user is to say the trigger word and wherein the predefined first user profile includes a repeat period for an amount of time to repeat the trigger word.
11. The method of claim 9 , wherein the trigger word is different from a predefined wake word of the voice-based interface.
12. The method of claim 8 , wherein the predefined first user profile includes a predefined rate of speech for the first user, and wherein the identifying includes detecting speech in the audio stream that differs from the predefine rate of speech.
13. The method of claim 8 , wherein the predefined first user profile includes a predefined tone of speech for the first user, and wherein the identifying includes detecting speech in the audio stream that differs from the predefined tone of speech.
14. The method of claim 1 , wherein the assistance action includes instructing a computing device of the first user to generate an audiovisual recording of the environment.
15. The method of claim 1 , wherein the assistance action includes instructing the computing device of the second user to generate an audiovisual alert.
16. The method of claim 1 , wherein the assistance action includes the computing device of the second user to generate an audiovisual recording of the environment.
17. A system, the system comprising:
a memory, the memory containing one or more instructions; and
a processor, the processor communicatively coupled to the memory, the processor, in response to reading the one or more instructions, configured to:
receive, from an audio transceiver of a computing device of a second user, an audio stream in an environment that includes audio of a first user, wherein the audio transceiver is integrally coupled to the computing device of the second user, and wherein the computing device of the second user is located in the environment;
detect, from the audio stream, an acoustic communication of the first user;
identify, from the audio stream and based on the acoustic communication, an audio intent trigger of the first user; and
initiate, in response to the audio intent trigger and by a voice-based interface, an assistance action for the first user, wherein the assistance action includes instructing a computing device of the first user to generate an audiovisual recording of the environment.
18. A computer program product, the computer program product comprising:
one or more computer readable storage media; and
program instructions collectively stored on the one or more computer readable storage media, the program instructions configured to:
receive, from an audio transceiver of a computing device of a second user, an audio stream in an environment that includes audio of a first user, wherein the audio transceiver is integrally coupled to the computing device of the second user, and wherein the computing device of the second user is located in the environment;
detect, from the audio stream, an acoustic communication of the first user;
identify, from the audio stream and based on the acoustic communication, an audio intent trigger of the first user; and
initiate, in response to the audio intent trigger and by a voice-based interface, an assistance action for the first user, wherein the assistance action includes instructing a computing device of a second user to generate an audiovisual alert.