Network conference management and arbitration via voice-capturing devices
Systems and methods are provided for managing a conference call with multiple voice-enabled and voice-capturing devices, such as smart speakers. Reproduced, duplicate voice commands can cause unexpected results in a conference call. The voice commands can be determined to be received from the same conference call. A voice command for a particular voice-enabled device can be selected based on an energy level of an audio signal, event data, time data, and/or user identification.
1. A system for managing a conference meeting, the system comprising:
an electronic data store; and
one or more computer hardware processors in communication with the electronic data store, the one or more computer hardware processors configured to execute computer-executable instructions to at least:
identify a plurality of voice-enabled devices connected to a particular conference call session, the plurality of voice-enabled devices comprising a first voice-enabled device and a second voice-enabled device, the first voice-enabled device associated with a first account different than a second account associated with the second voice-enabled device;
generate a group of voice-enabled devices from the plurality of voice-enabled devices;
identify a voice command received by the first voice-enabled device and a first timestamp, wherein the first timestamp indicates a first time when a first audio signal containing the voice command was received by the first voice-enabled device;
determine, using the group, that the voice command was also received by the second voice-enabled device;
identify a second timestamp, wherein the second timestamp indicates a second time when a second audio signal containing the voice command was received by the second voice-enabled device, wherein the first voice-enabled device and the second voice-enabled device are in different rooms, and wherein voice input from a conference call participant is received by the first voice-enabled device and the second voice-enabled device;
determine that the first timestamp and the second timestamp are within a threshold period of time;
determine that the voice command corresponds to a command to leave a conference call;
select the first voice-enabled device, instead of the second voice-enabled device, based on the first timestamp being earlier than the second timestamp; and
execute the voice command based on the selecting, wherein execution of the voice command causes the first voice-enabled device to disconnect from the conference call.
2. The system of claim 1 , wherein a difference in time between the first timestamp and the second timestamp is based on latency for transmitting data between a first location and a second location.
3. The system of claim 1 , wherein a first location comprises the first voice-enabled device, and wherein a second location comprises the second voice-enabled device and a speaker device separate from the second voice-enabled device, and wherein the second voice-enabled device is configured to generate the second audio signal in response to receiving a sound wave emitted from the speaker device.
4. The system of claim 3 , wherein the sound wave is a reproduction of the first audio signal from the first location.
5. The system of claim 1 , wherein the first voice-enabled device and the second voice-enabled device are time synchronized.
6. The system of claim 1 , wherein identifying the first voice command for the first voice-enabled device further comprises:
performing automatic speech recognition on the first audio signal.
7. A computer-implemented method comprising:
identifying a plurality of voice-enabled devices connected to a particular conference call session, the plurality of voice-enabled devices comprising a first voice-enabled device and a second voice-enabled device, the first voice-enabled device associated with a first account different than a second account associated with the second voice-enabled device;
generating a group of voice-enabled devices from the plurality of voice-enabled devices;
identifying a voice command from the first voice-enabled device and a first timestamp, wherein the first timestamp indicates a first time when a first audio signal containing the voice command was received by the first voice-enabled device;
determining, using the group, that the voice command was received by the second voice-enabled device;
identifying a second timestamp, wherein the second timestamp indicates a second time when a second audio signal containing the voice command was received by the second voice-enabled device, wherein voice input from a conference call participant is received by the first voice-enabled device and the second voice-enabled device;
selecting the first voice-enabled device, from the first voice-enabled device and the second voice-enabled device, based on the first timestamp being earlier than the second timestamp; and
executing the voice command for the first voice-enabled device instead of the second voice-enabled device.
8. The computer-implemented method of claim 7 , further comprising:
determining that the first timestamp and the second timestamp are within a threshold period of time.
9. The computer-implemented method of claim 7 , wherein a first location comprises the first voice-enabled device, and wherein a second location comprises the second voice-enabled device, a speaker device separate from the second voice-enabled device, and a microphone separate from the second voice-enabled device, and wherein the microphone is configured to generate the second audio signal in response to receiving a sound wave emitted from the speaker device.
10. The computer-implemented method of claim 9 , wherein the sound wave is a reproduction of the first audio signal from the first location.
11. The computer-implemented method of claim 7 , wherein determining that the voice command was received by the second voice-enabled device further comprises:
determining that the second audio signal originated from the group.
12. The computer-implemented method of claim 7 , further comprising:
retrieving, from the particular conference call session, a plurality of voice-enabled device identifiers, wherein each device identifier of the plurality of voice-enabled device identifiers corresponds to a voice-enabled device connected to the particular conference call session.
13. The computer-implemented method of claim 7 , wherein generating the group further comprises:
determining the group based on a meeting invite, wherein the meeting invite includes information identifying the plurality of voice-enabled devices.
14. A system comprising:
one or more computer hardware processors, the one or more computer hardware processors configured to execute computer-executable instructions to at least:
identify a plurality of voice-enabled devices connected to a particular conference call session, the plurality of voice-enabled devices comprising a first voice-enabled device and a second voice-enabled device, the first voice-enabled device associated with a first account different than a second account associated with the second voice-enabled device;
generate a group of voice-enabled devices from the plurality of voice-enabled devices;
identify a voice command from the first voice-enabled device and a first timestamp, wherein the first timestamp indicates a first time when a first audio signal containing the voice command was received by the first voice-enabled device;
determine, using the group, that the voice command was received by the second voice-enabled device;
identify a second timestamp, wherein the second timestamp indicates a second time when a second audio signal containing the voice command was received by the second voice-enabled device, wherein voice input from a conference call participant is received by the first voice-enabled device and the second voice-enabled device;
select the first voice-enabled device, from the first voice-enabled device and the second voice-enabled device, based on the first timestamp being earlier than the second timestamp; and
execute the voice command for the first voice-enabled device instead of the second voice-enabled device.
15. The system of claim 14 , wherein the one or more computer hardware processors are further configured to receive the first timestamp from the first voice-enabled device.
16. The system of claim 14 , wherein a first room comprises the first voice-enabled device, wherein the second voice-enabled device is located in a second room with a speaker device separate from the second voice-enabled device, and wherein the second voice-enabled device is configured to generate the second audio signal in response to receiving a sound wave emitted from the speaker device.
17. The system of claim 16 , wherein the sound wave is a reproduction of the first audio signal the first voice-enabled device in the first room.
18. The system of claim 14 , wherein to determine that the voice command was received by the second voice-enabled device, the one or more computer hardware processors are further configured to:
determine that both the first audio signal and the second audio signal originated from the group.
19. The system of claim 14 , wherein to generate the group, the one or more computer hardware processors are further configured to:
retrieve event data associated with a meeting involving a plurality of locations; and
determine the plurality of voice-enabled device identifiers based on the event data, wherein the group comprises the plurality of voice-enabled device identifiers.
20. The system of claim 19 , wherein to determine the plurality of voice-enabled device identifiers based on the event data, the one or more computer hardware processors are further configured to:
retrieve, from the event data, a plurality of location identifiers; and
for each location identifier of the plurality of location identifiers, retrieve a voice-enabled device identifier for a device at a location corresponding to the location identifier.