Intelligent voice enable device searching method and apparatus thereof
An intelligent voice enable device searching method and apparatus are disclosed. A method for searching a plurality of voice enable devices according to one embodiment of the present disclosure includes receiving first device information from a first device receiving a wake-up voice; searching a first account associated with the first device based on the first device information; searching devices of a first group registered in the first account; searching a second account associated with a second device other than the first device among the devices of the first group; searching devices of a second group registered in the second account; searching devices of a third group sharing an IP address with the devices of the first group or the devices of the second group; and selecting a voice enable device to respond to the wake-up voice among the devices of the first group, the second group, and the third group. The method has an effect that a device that responds to a wake-up voice may be searched more accurately than in a conventional approach.
1. A method for searching a plurality of voice enable devices included in a single communication network, performed by a voice enable devices searching apparatus, the method comprising:
receiving, by a transceiver included in the voice enable devices searching apparatus, first device information from a first device receiving a wake-up voice;
searching, by a processor included in the voice enable devices searching apparatus, a first account associated with the first device based on the first device information;
searching, by the processor, devices of a first group registered in the first account;
searching, by the processor, a second account associated with a second device other than the first device among the devices of the first group;
searching, by the processor, devices of a second group registered in the second account;
searching, by the processor, devices of a third group sharing an IP address with the devices of the first group or the devices of the second group; and
selecting, by the processor, a voice enable device to respond to the wake-up voice among the devices of the first group, the second group, and the third group.
2. The method of claim 1 , wherein the first device information includes at least one of a device ID of the first device, an IP address shared by the first device, or a first audio signal generated by the first device recognizing the wake-up voice.
3. The method of claim 2 , further comprising:
receiving a second audio signal from a second device within a threshold time duration after receiving the first device information;
based on the second device being included in the first group, the second group, or the third group, determining whether a speaker of the second audio signal is identical with a speaker of the first audio signal; and
based on the speaker of the second audio signal being identical with the speaker of the first audio signal, selecting the voice enable device among the devices of the first group, the second group, and the second device.
4. The method of claim 3 , further comprising:
based on (i) the second device not being included in the first group, the second group, or the third group or (ii) the speaker of the second audio signal not being identical with the speaker of the first audio signal, generating a fourth group including the second device; and
selecting a voice enable device to respond to the second audio signal among devices of the fourth group.
5. The method of claim 4 , further comprising:
searching a plurality of third accounts associated with the second device;
searching a plurality of third devices registered in the plurality of third accounts;
searching a plurality of fourth devices sharing an IP address with the plurality of third devices; and
selecting a voice enable device to respond to the wake-up voice among the plurality of third devices and the plurality of fourth devices.
6. The method of claim 3 , wherein determining whether the speaker of the second audio signal is identical with the speaker of the first audio signal includes applying Gaussian mixture model (GMM), support vector machine (SVM), or deep neural network (DNN) to the first audio signal and the second audio signal.
7. The method of claim 4 , further comprising deleting each of the first group, the second group, the third group, and the fourth group after a threshold time duration has elapsed after each of the first group, the second group, the third group, and the fourth group has been generated.
8. An apparatus for searching a plurality of voice enable devices, the apparatus comprising:
a transceiver for receiving first device information from a first device receiving a wake-up voice;
a memory including at least one instruction; and
a processor executing the at least one instruction,
wherein executing the at least one instruction causes the processor to perform operations comprising:
searching a first account associated with the first device based on the first device information;
searching devices of a first group registered in the first account;
searching a second account associated with a second device other than the first device among the devices of the first group;
searching devices of a second group registered in the second account;
searching devices of a third group sharing an IP address with the devices of the first group or the devices of the second group; and
selecting a voice enable device to respond to the wake-up voice among the devices of the first group, the second group, and the third group.
9. The apparatus of claim 8 , wherein the first device information includes at least one of a device ID of the first device, an IP address shared by the first device, or a first audio signal generated by the first device recognizing the wake-up voice.
10. The apparatus of claim 9 , wherein the operations comprise:
receiving a second audio signal from a second device within a threshold time duration after receiving the first device information;
based on the second device being included in the first group, the second group, or the third group, determining whether a speaker of the second audio signal is identical with a speaker of the first audio signal; and
based on the speaker of the second audio signal being identical with the speaker of the first audio signal, selecting the voice enable device among the devices of the first group, the second group, and the second device.
11. The apparatus of claim 10 , wherein the operations comprise:
based on (i) the second device not being included in the first group, the second group, or the third group or (ii) the speaker of the second audio signal not being identical with the speaker of the first audio signal, generating a fourth group including the second device; and
selecting a voice enable device to respond to the second audio signal among devices of the fourth group.
12. The apparatus of claim 11 , wherein the operations comprise:
searching a plurality of third accounts associated with the second device;
searching a plurality of third devices registered in the plurality of third accounts;
searching a plurality of fourth devices sharing an IP address with the plurality of third devices; and
selecting a voice enable device to respond to the wake-up voice among the plurality of third devices and the plurality of fourth devices.
13. The apparatus of claim 12 , wherein the operations comprise applying Gaussian mixture model (GMM), support vector machine (SVM), or deep neural network (DNN) to the first audio signal and the second audio signal.
14. The apparatus of claim 11 , wherein the operations comprise deleting each of the first group, the second group, the third group and the fourth group after a threshold time duration has elapsed after each of the first group, the second group, the third group and the fourth group has been generated.