Smart speaker wake-up method and device, smart speaker and storage medium
The present disclosure discloses a smart speaker wake-up method, a smart speaker wake-up device, a smart speaker and a storage medium, relates to the technical field of speech recognition. The method of the present disclosure is applied to a wireless network including two or more smart speakers, and a specific implementation thereof is: receiving, speech information including a wake-up word; performing a recognition processing to the speech information to obtain identification information corresponding to the wake-up word; and waking up one smart speaker in the wireless network to enter listening state according to the identification information. The present disclosure may be applied to a scenario where multiple smart speakers coexist, so as to quickly select one smart speaker that is most likely to be wakened, avoiding a chaotic speech interaction caused by multiple smart speakers being wakened simultaneously, improving efficiency and quality of speech interaction and achieving better user experience.
1. A smart speaker wake-up method, which is applied to a wireless network comprising two or more smart speakers, comprising:
receiving speech information comprising a wake-up word;
performing a recognition processing to the speech information to obtain identification information corresponding to the wake-up word, wherein the identification information comprises time at which the wake-up word is recognized by any one smart speaker in the wireless network or a speech intensity corresponding to the wake-up word is recognized by any one smart speaker in the wireless network; and
waking up one smart speaker in the wireless network to enter listening state according to the time at which the wake-up word is recognized by any one smart speaker in the wireless network and time at which the wake-up word is recognized by other smart speakers in the wireless network or according to the speech intensity corresponding to the wake-up word is recognized by any one smart speaker in the wireless network and a speech intensity corresponding to the wake-up word is recognized by other smart speaker in the wireless network.
2. The method according to claim 1 , wherein the performing a recognition processing to the speech information to obtain identification information corresponding to the wake-up word, comprises:
recognizing the wake-up word from the speech information and recording a first timestamp corresponding to the recognition of the wake-up word.
3. The method according to claim 2 , wherein before the waking up one smart speaker in the wireless network to enter listening state according to the identification information, also comprising:
transmitting the first timestamp to other smart speakers in the wireless network by way of broadcasting; and
receiving a second timestamp transmitted by other smart speakers in the wireless network, wherein the second timestamp is referred to as time corresponding to a recognition of the wake-up word by other smart speakers.
4. The method according to claim 3 , wherein the waking up one smart speaker in the wireless network to enter listening state according to the identification information, comprises:
comparing the time corresponding to the first timestamp with the time corresponding to the second timestamp;
giving up to wake up if the time of at least one second timestamp is earlier than the time of the first timestamp; and
waking up to enter the listening state if none of the time of the second timestamp is earlier than the time of the first timestamp.
5. The method according to claim 1 , wherein the performing a recognition processing to the speech information to obtain identification information corresponding to the wake-up word, comprises:
recognizing the wake-up word from the speech information, and recording a first speech intensity corresponding to the wake-up word.
6. The method according to claim 5 , wherein before the waking up one smart speaker in the wireless network to enter listening state according to the identification information, also comprising:
transmitting the first speech intensity to other smart speakers in the wireless network by way of broadcasting; and
receiving a second speech intensity transmitted by other smart speakers in the wireless network, wherein the second speech intensity is referred to as a speech intensity corresponding to a recognized wake-up word by other smart speakers.
7. The method according to claim 6 , wherein the waking up one smart speaker in the wireless network to enter listening state according to the identification information, comprises:
comparing the first speech intensity with the second speech intensity;
giving up to wake up if at least one second speech intensity is larger than the first speech intensity; and
waking up to enter the listening state if none of the second speech intensity is larger than the first speech intensity.
8. The method according to claim 1 , wherein the smart speaker in the wireless network is located in a preset geographic range, and there exist at least two smart speakers with different account numbers in the wireless network.
9. A smart speaker system, comprising:
at least one processor; and
a memory in communication connection with the at least one processor; wherein,
the memory stores instruction executable by the at least one processor, the instruction is executed by the at least one processor, so as to make the at least one processor for executing the following steps while being applied to a wireless network comprising two or more smart speakers:
receiving speech information comprising a wake-up word;
performing a recognition processing to the speech information to obtain identification information corresponding to the wake-up word, wherein the identification information comprises time at which the wake-up word is recognized by any one smart speaker in the wireless network or a speech intensity corresponding to the wake-up word is recognized by any one smart speaker in the wireless network; and
determining whether to wake up the smart speaker itself to enter listening state according to the time at which the wake-up word is recognized by any one smart speaker in the wireless network and time at which the wake-up word is recognized by other smart speakers in the wireless network or according to the speech intensity corresponding to the wake-up word is recognized by any one smart speaker in the wireless network and a speech intensity corresponding to the wake-up word is recognized by other smart speaker in the wireless network.
10. The smart speaker according to claim 9 , wherein the performing a recognition processing to the speech information to obtain identification information corresponding to the wake-up word, comprises:
recognizing the wake-up word from the speech information and recording a first timestamp corresponding to the recognition of the wake-up word.
11. The smart speaker according to claim 10 , wherein before determining whether to wake up the smart speaker itself to enter listening state according to the identification information, also comprising:
transmitting the first timestamp to other smart speakers in the wireless network by way of broadcasting; and
receiving a second timestamp transmitted by other smart speakers in the wireless network, wherein the second timestamp is referred to as time corresponding to a recognition of the wake-up word by other smart speakers.
12. The smart speaker according to claim 11 , wherein determining whether to wake up the smart speaker itself to enter listening state according to the identification information, comprises:
comparing the time corresponding to the first timestamp with the time corresponding to the second timestamp;
giving up to wake up if the time of at least one second timestamp is earlier than the time of the first timestamp; and
waking up to enter the listening state if none of the time of the second timestamp is earlier than the time of the first timestamp.
13. The smart speaker according to claim 10 , wherein the smart speaker in the wireless network is located in a preset geographic range, and there exist at least two smart speakers with different account numbers in the wireless network.
14. The smart speaker according to claim 9 , wherein the performing a recognition processing to the speech information to obtain identification information corresponding to the wake-up word, comprises:
recognizing the wake-up word from the speech information, and recording a first speech intensity corresponding to the wake-up word.
15. The smart speaker according to claim 14 , wherein before determining whether to wake up the smart speaker itself to enter listening state according to the identification information, also comprising:
transmitting the first speech intensity to other smart speakers in the wireless network by way of broadcasting; and
receiving a second speech intensity transmitted by other smart speakers in the wireless network, wherein the second speech intensity is referred to as a speech intensity corresponding to a recognized wake-up word by other smart speakers.
16. The smart speaker according to claim 15 , wherein determining whether to wake up the smart speaker itself to enter listening state according to the identification information, comprises:
comparing the first speech intensity with the second speech intensity;
giving up to wake up if at least one second speech intensity is larger than the first speech intensity; and
waking up to enter the listening state if none of the second speech intensity is larger than the first speech intensity.
17. The smart speaker according to claim 14 , wherein the smart speaker in the wireless network is located in a preset geographic range, and there exist at least two smart speakers with different account numbers in the wireless network.
18. The smart speaker according to claim 9 , wherein the smart speaker in the wireless network is located in a preset geographic range, and there exist at least two smart speakers with different account numbers in the wireless network.
19. A non-transitory computer readable storage medium having a computer instruction stored therein, wherein, the computer instruction is configured to make the computer execute the method according to claim 1 .
20. A smart speaker wake-up method, comprising:
receiving speech information; and
waking up, if the speech information comprises a wake-up word, one smart speaker in a wireless network to enter listening state according to identification information corresponding to the wake-up word, wherein the identification information comprises time at which the wake-up word is recognized by any one smart speaker in the wireless network or a speech intensity corresponding to the wake-up word is recognized by any one smart speaker in the wireless network;
wherein the waking up one smart speaker in a wireless network to enter listening state according to identification information corresponding to the wake-up word, comprises:
waking up one smart speaker in the wireless network to enter listening state according to the time at which the wake-up word is recognized by any one smart speaker in the wireless network and time at which the wake-up word is recognized by other smart speakers in the wireless network or according to the speech intensity corresponding to the wake-up word is recognized by any one smart speaker in the wireless network and a speech intensity corresponding to the wake-up word is recognized by other smart speaker in the wireless network.